Temporal Distribution Shift

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 35

Sep 27, 2026cs.LG

RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift

Contextual specialization can improve forecasting accuracy, but a correction selected on one historical interval may become unreliable under temporal distribution shift. To address this issue, we propose RAEGL, a Risk-Aware Evidence-Gated Learning framework for selective contextual forecasting. RAEGL retains a validated global predictor by default and activates a contextual residual only when pre-deployment evidence supports its use. The framework separates candidate selection from gate calibration and jointly evaluates randomization significance, practically meaningful gain, and temporal stability. Experiments on real-world audits and controlled panels show how RAEGL can prevent harmful contextual deployment while making conservative opportunity costs explicit. In a reconstructed Our World in Data audit, exact fallback avoids RMSE degradations of 0.0960 and 0.0239 caused by two validation-selected corrections. In a sealed World Development Indicators evaluation, a region-based correction passes the randomization test but is withheld because its gain is only 0.000092, its country-clustered 95% confidence interval crosses zero, and only 0.02% of bootstrap replicates reach the practical threshold. In controlled panels, the stability- and support-aware extension activates in 97.2% of strong, stable-context runs while rejecting all high-drift settings. These results support RAEGL as an auditable, evidence-based mechanism for managing contextual deployment risk and as a conservative alternative to validation-driven contextual selection.

Yifan Guo

Stony Brook University

Distribution Shift Selective Prediction Time Series Forecasting Temporal Distribution Shift

Sep 21, 2026cs.CR

Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection

Malware detection is a critical task in cybersecurity, and graph neural networks over control flow graphs have shown promising results for it. However, detectors are usually evaluated on a random split of a corpus collected over a single period, which cannot show how well a model generalizes to later samples. This study addresses that limitation with a strict temporal split: every model is trained on one period and scored once on a later one. Two corpora of control flow graphs, each node carrying 37 features, were extracted statically from 1,989 Windows portable executables: 459 graphs from 2024-2025 for training and 223 from 2026 for evaluation. Twelve variants and a flat-feature control were trained on the earlier corpus. The choice of message-passing operator changes robustness to the shift significantly, and every pairwise gap that survives correction separates an aggregating architecture from one built around a learned attentional readout. The ranking also reverses: the flat control, which sees node features but no topology, is the best in-distribution model and among the worst across the boundary, so a conventional benchmark would have rejected message passing. Neither recalibration nor ensembling substitutes for the operator choice. Attributions do not shift, but explanation validity is architecture-specific, and the most accurate operator on the later corpus is the hardest to explain. An architecture derived from the finding matches the best searched operator without search. The shift affects both malware and benign classes alike, so these are results about robustness to distribution shift, not malware evolution.

Md. Asif Sajeed, Md. Nazrul Islam Mondal, Md Ashraful Hossen Akash

Department of Computer Science and Engineering, Rajshahi University of Engineering & Technology, Rajshahi, 6204, Bangladesh

Graph Neural Networks Distribution Shift Explanation Stability GNN Explainability Temporal Distribution Shift Malware Detection

Sep 14, 2026stat.ME

The Anatomy and Boundary of Adaptation under Temporal Tabular Shift

Prequential adaptation of frozen tabular foundation models under temporal drift, with each label revealed only after prediction, helps some deployments and harms others, yet current practice does not predict which. We study the sources and limits of these gains. A diagnostic anatomy attributes gains to four recurring mechanisms under a streaming protocol that removes three optimistic biases and quantifies a fourth. Within an agnostic total-variation drift class, the target conditional is only partially identified: its identified-set diameter, the \emph{wall}, is irreducible from unlabeled data uniformly in sample size. A second, orthogonal

L^2

projection wall quantifies what the frozen representation cannot express. Two canonical mechanism priors collapse the first wall. Under stated nuisance-rate conditions, the wall can be estimated from labeled historical windows at a

\sqrt N

rate above the margin threshold

\gamma^\star=d_0/(2\alpha_s)

. At

\gamma=0

, the conditional lower-bound program depends on an open affinity estimate; the positive-margin lower branch also remains open. Semi-synthetic data illustrate the finite-sample mechanism with calibrated exponents. Stream-level proxies on eight industrial streams fall on the difficult side under a stated roughness bound, while the equality case

\gamma=\gamma^\star

remains unresolved.

Tianyu Wang, Xi Vincent Wang, Lihui Wang +2

Department of Production Engineering, KTH Royal Institute of Technology, Stockholm, Sweden · Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China

Tabular Foundation Models Distribution Shift Partial Identification Temporal Distribution Shift

Sep 1, 2026cs.LG

When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting

Online adaptation can help edge time-series forecasting under distribution drift, but its measured benefit is sensitive to evaluation choices. We study six public multivariate streams, including building-sensor and smart-meter data, under a leakage-free streaming protocol. We identify two additional sources of comparison bias. First, the warmup budget of the static baseline has a two-sided effect: insufficient warmup undertrains the baseline, whereas excessive warmup can degrade its pre-drift generalization. Across six dataset-backbone settings, the estimated adaptation benefit changes by 3.0 to 18.8 percentage points (pp) over the 1,000-20,000-step warmup range. Second, comparing SGD with momentum (SGD+m) and Adam at a shared default learning rate conflates optimizer quality with rate sensitivity. We select both the warmup budget and each optimizer's online rate using a held-out pre-drift validation slice without accessing test data. Under this validation-only procedure, Adam outperforms SGD+m in 310 of 360 evaluated cells, while 4 Adam cells remain below the static baseline. We further characterize accuracy against adaptation-state memory and A100-measured per-update latency for full, head-only, and calibration-based adaptation. In the evaluated PatchTST frontier settings, several parameter-efficient variants are nondominated on the adaptation-state-memory axis. Smart-meter analyses also show that reported gains depend on meter-selection rules. These findings support a validation-only commissioning procedure, while target-device latency and energy remain to be measured. Code, data, and all reported numbers: https://github.com/keiotakmin/tsf-edge-adaptation.

Takumi Fujimoto, Hiroaki Nishi

School of Science for Open and Environmental Systems, Graduate School of Science and Technology, Keio University, Yokohama, Japan

Multivariate Time Series Forecasting Learning Rate Scheduling Continual Test-Time Adaptation Edge Computing Temporal Distribution Shift

Jul 27, 2026cs.LG

When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction

Generative models of temporal graphs are trained on one stretch of an evolving network and deployed on the next, and they degrade badly in the gap. We show this degradation is derivable, general, and not fixable from observations. The masked flow-matching loss decomposes exactly, with no independence assumption, into an irreducible entropy plus a divergence whose derivative along the training path is positive precisely for structures rare during training and common at deployment, diverging as their training probability goes to zero. Empirically the trade-off is a power law with exponent

-0.605

(

R^2=0.9977

), and drift raises the sampler's error floor without changing how many steps reach it: across seven well-powered conditions the drift-period marginal error varies by at most

6\%

over a

50\times

range of sampling budgets, while the floor sits

2.2\times

to

34.3\times

above the in-period floor. Because the deployment period is observed, correction looks like a matter of measurement. It is not. We prove that any corrector measurable with respect to past observations leaves at least the conditional variance of the statistic it tracks, and that trend extrapolation beats trusting the last observation only when

μ^2>v(1-2ρ)

. Both premises are measurable and both go the wrong way: the drift is trendless and mean-reverting, with a one-step innovation as large as the drift itself. An oracle removes

60\%

of the error, the best observation-based corrector recovers

5.7\%

of that, and extrapolation is strictly worse than doing nothing clever.

Tianpeng Li, Xuan Guo, Wenjun Wang +2

College of New Media and Communication, Tianjin University · School of Artificial Intelligence, Tianjin University · School of Cyberspace Security,Hangzhou Dianzi University

Flow Matching Distribution Shift Graph Generation Generative Modeling Flow-Based Generative Modeling Drifting Models+1

Jul 10, 2026cs.CV

Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification

Long-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts. Although recent vision-language models provide strong pretrained visual representations, adapting them to longitudinal ecological settings remains challenging, particularly under identity and temporal distribution shifts. We present a parameter-efficient CLIP adaptation framework for animal ReID and introduce a continuous metadata-conditioning mechanism that incorporates numerical attributes directly into the prompt representation during training. While low-rank visual adaptation, prompt-based supervision, and cross-modal alignment provide the adaptation framework, the proposed metadata-conditioning strategy constitutes the primary methodological contribution. By preserving the continuous structure of numerical metadata rather than discretizing it into textual categories, the proposed approach enables smooth modulation of the embedding space during training while maintaining a purely visual inference pipeline. Experiments on a seven-year longitudinal fish dataset and multiple wildlife benchmarks demonstrate improved performance under closed-set, open-set, and time-aware evaluation protocols. The results demonstrate that continuous metadata conditioning improves robustness to longitudinal appearance variation and temporal distribution shifts, while parameter-efficient adaptation enables a purely visual inference pipeline without requiring metadata at test time. Code and evaluation splits can be found at: https://github.com/AnilOsmanTur/MetaPrompt-ReID.

Anil Osman Tur, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsen +1

Department of Computer Science, University of Verona, Verona, 37134, Italy · Institute of Marine Research, Nye Flødevigveien 20, 4817 His, Norway · University of Agder, Centre for Coastal Research, Grimstad, 4604, Norway

Animal Re-Identification Distribution Shift VLM Adaptation Visual Prompt Learning Temporal Distribution Shift

Jul 10, 2026cs.LG

Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation

Temporal knowledge graphs (TKGs) represent evolving relational systems, whose underlying data-generating processes often change over time. Yet, TKG forecasting models are commonly evaluated only on empirical benchmark datasets that provide limited insight into the models' robustness to such distribution shifts. Recognising this issue, we study TKG forecasting under controlled shift environments using a synthetic TKG generator that encodes three temporal and structural properties -- recurrence, homophily, and periodicity -- as data-generating mechanisms. This allows us to evaluate seven forecasting architectures under stationary and shifting regimes. Our experiments suggest that robustness in TKG forecasting is highly signal-dependent. Recurrence-based and periodic regularities are largely recoverable under stationary conditions, and simple memory-based baselines can be competitive when recurrence dominates the data. However, structural breaks reveal limitations in model adaptivity, with shifts in latent entity-community structure posing the strongest challenge in our study. Overall, our findings improve the understanding of the capabilities and limitations of current TKG models confronted with temporal distribution shifts.

Konrad Özdemir, Julia Gastinger, Lukas Kirchdorfer +1

Data and Web Science Group, University of Mannheim, Germany · SAP Signavio, Walldorf, Germany

Distribution Shift Temporal Link Prediction Temporal KGs Temporal Distribution Shift

Jul 7, 2026cs.LG

Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift

Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems. However, the extent to which architectural choices and their associated inductive biases affect temporal robustness remains insufficiently understood. We present a systematic empirical comparison of temporal robustness across three heterogeneous, time-indexed domains encompassing image classification, multi-label text classification, and text regression tasks. Using a unified evaluation framework based on temporal drift matrices, we train models on cumulative historical data and evaluate their performance on both earlier and later time periods, thereby quantifying cross-temporal generalization. Our study spans model families ranging from simple multilayer perceptrons and convolutional networks to recurrent networks and pretrained Transformer-based encoders. Collectively, the results show that architectural inductive biases systematically shape temporal robustness: models whose inductive biases lead them to exploit localized, highly discriminative features attain the highest in-distribution accuracy, yet those features are often the ones that change most over time, so these models degrade fastest, while pretrained encoders that draw on coarser, more stable representations drift more gradually. These observations offer practical guidance for selecting architectures for real-world systems subject to temporal drift.

Robin Holzinger, Riccardo Colletti

Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA

Distribution Shift Robustness Neural Network Generalization Neural Network Robustness Temporal Distribution Shift

Jul 6, 2026cs.LG

Domain-Adaptive Climate Downscaling Under Temporal Distribution Shift

Deep-learning-based climate downscaling aims to learn relationships from historical low-resolution (LR) and high-resolution (HR) climate data to generate HR climate projections. However, this setting faces a temporal out-of-distribution (OOD) challenge: models trained on historical data are commonly applied to future projections whose distributions may differ substantially from the training period. This study investigates temporal OOD shift for daily temperature downscaling over the Continental United States using paired LR-HR model simulations. We propose a temporal domain-adaptive downscaling framework that combines supervised HR reconstruction on historical data with domain alignment between historical and future climate distributions. Experiments across future validation periods show that the proposed domain-adaptive model consistently outperforms statistical and deep-learning-based bias-correction methods, with the largest gains occurring when the temporal distribution shift is strongest. Spatial analyses indicate stronger improvements over high-elevation and topographically complex regions, along with higher spatiotemporal correlation with the HR target. The extreme analysis shows that domain adaptation also reduces upper-tail temperature bias relative to the non-adaptive model. These results demonstrate that temporal domain adaptation can improve the robustness of HR climate projections under non-stationary climate conditions.

Shuochen Wang, Nishant Yadav, Auroop R. Ganguly

Sustainability and Data Sciences Laboratory, Northeastern University · Microsoft · AI for Climate and Sustainability, The Institute for Experiential AI, Northeastern University

Distribution Shift Robustness Domain Adaptation Climate Modeling Climate Downscaling Temporal Distribution Shift

Jun 23, 2026cs.LG

When Multi-Sensor Fusion Fails to Generalize: Cattle Posture Classification Under Animal-Level and Temporal Distribution Shift

Automated cattle posture-classification systems frequently report near-perfect accuracy, yet their robustness under realistic deployment conditions remains largely unknown. In particular, it is unclear whether multimodal sensor fusion improves generalisation or leads models to rely on context-specific signals that fail under distribution shift. Here, we evaluate the robustness of automated posture classification (lying versus standing) using collar accelerometers, rumen-bolus sensors, and environmental measurements collected from a pasture-based beef cattle herd across two consecutive years (2024-2025). XGBoost served as the primary model, with Logistic Regression, Random Forest, and Long Short-Term Memory networks evaluated as comparative baselines. Model robustness was assessed under progressively more stringent evaluation protocols, ranging from conventional random train-test splits to leave-one-animal-out validation and cross-year evaluation on an independent cohort of previously unseen animals recorded one year later. While multimodal models achieved strong within-year performance (macro-F1 0.94), the performance declined substantially under cross-year evaluation (macro-F1 0.49). Explainability analysis revealed persistent reliance on rumen-bolus activity and environmental variables even when predictive performance deteriorated. Distribution-shift diagnostics further confirmed substantial differences in feature distributions between recording years. Our findings demonstrate that commonly used evaluation protocols can substantially overestimate real-world performance and that multimodal sensor fusion may reduce, rather than improve, robustness under temporal distribution shift. More broadly, the results highlight that benchmark accuracy alone is insufficient to assess deployment readiness and underscore the need for robustness-centred evaluation in livestock-monitoring research.

Leutrim Uka, Severino Pinto, Gundula Hoffmann +1

Institute of Computer Science, University of Potsdam, Potsdam, Germany. · Department of Sensors and Modelling, Leibniz Institute for Agricultural Engineering and Bioeconomy - ATB, Potsdam, Germany. · Department of Data Science in Bioeconomy, Leibniz Institute for Agricultural Engineering and Bioeconomy - ATB, Potsdam, Germany.

Distribution Shift Robustness Distribution Shift Animal Behavior Analysis Temporal Distribution Shift Multimodal Sensor Fusion

Jun 18, 2026stat.ML

Betting on Moments: Legendre Jumper Martingales for Online Exchangeability Testing

A fundamental assumption in statistics and machine learning is that ``the future looks like the past,'' formalized as exchangeability: the joint data distribution is order-invariant. In practice, this assumption is often violated due to distribution shifts over time. Early detection of exchangeability violations is crucial to prevent performance degradation and enable timely interventions like model retraining. Conformal test martingales offer a flexible, distribution-free framework for sequential exchangeability testing with guaranteed false-alarm rate control by betting against the uniformity of conformal p-values. While alternatives such as plug-in martingales and mixture-based strategies exist, computationally efficient baselines like the Simple Jumper are limited to detecting mean location shifts. We propose a family of conformal test martingales based on shifted Legendre polynomials that extend the Simple Jumper to higher-order moments. The Simple Legendre Jumper replaces linear betting functions with polynomials of arbitrary degree, enabling rapid detection of variance, skewness, and other higher-order deviations. The Product Legendre Jumper combines multiple polynomial degrees into a single betting function but suffers from exponential state-space growth, termed the jumping tax. To resolve this, we introduce the Variational Legendre Jumper, which employs a mean-field approximation to reduce complexity to constant time per step with minimal power loss, providing an expressive, scalable framework for real-time distribution shift monitoring.

Johan Hallberg Szabadváry

Department of Mathematics, Stockholm University

Conformal Prediction Distribution Shift Detection Change-Point Detection Sequential Hypothesis Testing Temporal Distribution Shift Statistical Hypothesis Testing

Jun 11, 2026cs.LG

EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models

JEPA-family world models use a static predictor whose weights do not adapt when test-time dynamics diverge from training. We compare two mechanisms for incorporating accumulated experience into a JEPA predictor under distribution shift: operand-side injection, where a compressed experience representation is added as a residual to the predictor's hidden state (EI-JEPA), and operator-side modulation, where the same representation generates low-rank weight deltas via LoRA applied to the predictor's weights (EPM-JEPA). On a pre-registered comparison (Moving MNIST, gravity shift), EPM-JEPA (D_shift^{n=50} = 0.7848 +/- 0.0078, three seeds) differs from EI-JEPA (0.8238) by delta = 4.74% - Outcome C: a null result - by our stated criterion, a valid outcome. As a secondary, non-pre-registered observation, EPM-JEPA improves 1.90% over a no-memory baseline (0.8000), consistently across seeds, while EI-JEPA underperforms the baseline, indicating the benefit is specific to weight-level modulation. Our primary contribution is a mechanism analysis: the D_shift^{n=50} trajectory reflects three independent dynamical processes - buffer cycling, EMA target drift, and an intrinsic LoRA settling transient of +0.021 - rather than convergence to equilibrium. These findings motivate PEM-JEPA, a physics-grounded successor addressing this dynamical-peak limitation.

Vedant Pandya

School of Artificial Intelligence and Data Engineering (SAIDE) Indian Institute of Technology Jodhpur

Test-Time Adaptation World Model Learning Joint-Embedding Predictive Architecture Temporal Distribution Shift Parameter-Efficient Fine-Tuning

Jun 10, 2026cs.LG

TEDD: Robust Detection of Unstable Temporal Features

When working with real-world temporal data, it is common to encounter features whose distribution is changing over time. The naive employment of Machine Learning models on this unstable data might lead to rapidly degrading performance, especially if the new distribution is much different from what was previously seen during training. In order to cope with this problem, it is critical to automatically identify features that are changing over time. With these features detected, data scientists and other practitioners will be able to mitigate the issue (for instance, by applying data transformations), deploying more robust models that retain high performance for longer periods of time. In this paper, we describe which temporal changes a feature should not suffer from, and propose TEDD, a technique to a) identify when a dataset might lead to an unstable Machine Learning model and b) automatically detect which features cause such lack of robustness. In order to achieve it, we leverage a regression model to highlight which features contribute to a good prediction of an instance's timestamp. We compare our approach to other methods in real and synthetic data, testing their detection capability on all simple change patterns. We show that our method: detects all types of basic changes, both for numerical and categorical features; can detect multivariate drifts; returns a comparable value measuring the amount of change of each feature; requires no parameter tuning; and is scalable both on number of features and instances of the dataset.

Ricardo Ribeiro Pereira, Bruno Casal Laraña, Nádia Soares +1

DCC/FCUP University of Porto Porto, Portugal · Feedzai Porto, Portugal · Mindera Porto, Portugal

Distribution Shift Robustness Distribution Shift Detection Change-Point Detection Temporal Distribution Shift

Jun 8, 2026cs.LG

Machine-Learning Emulation of Satellite Greenhouse Gas Retrievals: Stability over Time

Retrieval algorithms are used to estimate atmospheric concentrations of greenhouse gases (GHGs), such as carbon dioxide (CO2) and methane (CH4), by solving inverse problems from high-spectral-resolution satellite radiance measurements. However, these algorithms are computationally expensive, which makes real-time estimation at scale difficult. Machine-learning models have therefore been proposed as fast emulators of retrieval algorithms. Most existing studies, however, evaluate them only on test data from the same period as the training data. We study the stability over time of such emulators using data from the Greenhouse Gases Observing SATellite (GOSAT). We show that prediction accuracy generally deteriorates when the test period moves away from the training period. We also show that including time as an input feature substantially improves XCH4 prediction for Lasso and neural-network models. Among the methods considered, a simple Lasso model performs as well as or better than more complex methods such as neural networks, and yields more stable predictions over time. We further validate the results using the Total Carbon Column Observing Network (TCCON), a ground-based observation network. On the TCCON-matched dataset, the time-augmented Lasso achieves errors against TCCON that are comparable to the disagreement between GOSAT and TCCON for both XCO2 and XCH4.

Nugzar Gognadze, Motonobu Kanagawa, Yu Someya +1

Data Science Department, EURECOM, 450 Route des Chappes, Biot, 06410, France

Surrogate Modeling Distribution Shift Remote Sensing Temporal Distribution Shift

Jun 5, 2026stat.ML

Empirical Transfer Operators and Finite-Sample Change Detection for Noisy Expanding Interval Maps

We study finite-sample change detection for one-dimensional noisy dynamical systems using partition-based empirical approximations of stationary behaviour. Given observations from an interval-valued process, we partition the state space, estimate a finite transition matrix from observed transitions between partition elements, and apply a small Doeblin-type regularisation to ensure a unique stationary distribution. From an initial reference segment, we compute a baseline empirical stationary distribution

\widehatπ_{0,ρ}

. For each later sliding window, we compute

\widehatπ_{t,ρ}

and define the score

S_t=\|\widehatπ_{t,ρ}-\widehatπ_{0,ρ}\|_1.

Large values of

S_t

indicate a change in stationary behaviour relative to the baseline. The statistic detects changes in invariant density or stationary law, but not all possible changes in transition dynamics. Under explicit assumptions on empirical transition concentration, finite-state stationary distribution stability, partition approximation, regularisation bias, and noise stability, we derive a finite-sample bound for the empirical stationary density. The bound separates sampling error, regularisation bias, partition approximation error, and noise bias. We then obtain a single-window false-alarm guarantee and a sufficient detection condition when the invariant density changes by more than the estimation error. We illustrate the method on synthetic noisy beta-map change-point experiments.

Aparna Rajput

Dynamical Systems Distribution Shift Detection Change-Point Detection Temporal Distribution Shift

Jun 2, 2026cs.LG

FlashbackCL: Mitigating Temporal Forgetting in Federated Learning

Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary. Flashback, the strongest recent FL method against cross-client (spatial) forgetting, uses monotonically accumulating per-class label counts as a knowledge proxy; this proxy becomes miscalibrated under temporal distribution shift and anchors the global model to an outdated class balance. We formalise temporal forgetting in FL with a per-phase metric isolated from protocol-level fluctuations and propose Flashback Continual Learning (FlashbackCL), a drop-in extension of Flashback with (i) temporally-decayed label counts; (ii) a device-aware replay buffer with Class-Balanced Reservoir Sampling (CBRS); and (iii) server-side active coreset curation on the public distillation set. The results show that FlashbackCL achieves 6.9% to 10.0% relative improvement relative to Flashback, on CIFAR-10 with 50 clients and three controlled temporal shift modes, while simultaneously reducing temporal forgetting by up to 68%. A 5-variant ablation identifies CBRS replay as the critical component. FlashbackCL also improves Flashback by 3.5 points on stationary CIFAR-100, suggesting that class-balanced replay regularises spatial heterogeneity as well as temporal shift.

Mubarak A. Ojewale, Adriana E. Chis, Jorge M. Cortes-Mendoza +2

Cloud Competency Centre, National College of Ireland, Dublin, Ireland

Distribution Shift Federated Continual Learning Non-IID Federated Learning Replay-Based Continual Learning Temporal Distribution Shift Federated Learning

Jun 1, 2026cs.LG

Regime-Arrival Uncertainty in Generalization Bounds under Distribution Shift

The standard generalization bounds assume that the training and deployment distributions are the same, or are static, and don't consider regime switching environments where the ratio of calm vs crisis states is different. This paper proposes a framework that generalizes regime-aware models by quantifying the extra risk due to regime composition mismatch, when distribution shifts are Markov-switching. We obtain an exact decomposition, separating regime mismatch from regime sensitivity; we extend the bound to beta-mixing data using the effective sample size corrected for the spectral gap; and we show a minimax lower bound for synthetic data and on 25 years of global equity indices. The proposed penalty is an ex post realized generalization gap, whereas the training-only estimator does not show significant correlation: the feature geometry of crises can be detected, but not the temporal arrival. Thus, the framework is not a forecast machine. Forecasting the composition of the future regime is an open question in the rare cases of regime change.

Prince Poudel

Independent researcher.

Distribution Shift Robustness Statistical Learning Theory Temporal Distribution Shift Generalization Bounds

May 30, 2026cs.LG

DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction

Sequential conformal prediction (CP) provides valid uncertainty quantification under the assumption of residual exchangeability. However, this assumption is often violated in real-world time series due to temporal dependencies and distributional shifts. While recent methods attempt to approximate exchangeability through reweighting, identifying optimal weights remains an open challenge. To address this limitation, we propose DistMatch, a binning-based method that recursively partitions residuals within a binary tree using the Kolmogorov-Smirnov (KS) statistic. We theoretically show that this partitioning induces approximately exchangeable leaves, thereby avoiding the need for reweighting. By applying quantile regression with online updates within each leaf, DistMatch enables locally adaptive inference and improves robustness to distributional shifts. Extensive experiments demonstrate that DistMatch outperforms existing sequential CP methods.

Enver Menadjiev, Jihyeon Seong, Jisu Yeo +1

Korea Advanced Institute of Science and Technology, South Korea · INEEJI, South Korea

Distribution Shift Robustness Conformal Prediction Distribution Matching Temporal Distribution Shift

May 29, 2026cs.LG

dashi: A Python library for Dataset Shift Characterization to Support Trustworthy AI Development and Deployment

The Artificial Intelligence (AI) life cycle requires a thorough understanding of the underlying data dynamics for robust, safe and cost-effective AI development and use. Dataset shifts are defined as changes between train and test data distributions. Whether occurring over time (temporal) or across different sites (multi-source), they can severely degrade model performance and compromise data quality. This is particularly important in health AI, where the safety and fundamental rights of patients can be severely affected by uncontrolled shifts both at training and operational stages. While the theoretical foundations of covariate, prior, and concept shifts are well established, there is a lack of accessible and comprehensive software tools to perform their analysis. We introduce dashi, an open-source Python library designed for the exploration, quantification, and characterization of dataset shifts. dashi provides a dual approach: an unsupervised approach that leverages information geometry and non-parametric statistical manifolds to data variability characterization and analysis (e.g., Information Geometric Temporal plots and Multi-Source Variability metrics like Global Probabilistic Deviation and Source Probabilistic Outlyingness), and a supervised approach that quantifies and characterizes model performance degradation. Both unsupervised and supervised approaches work across user-defined temporal and domain/source batches. We demonstrate the utility of dashi on three simulated and real-world health AI case studies on gestational diabetes mellitus, COVID-19 and emergency medical dispatch. By providing interactive visual analytics and variability metrics, dashi supports trustworthiness of AI life cycle stages enabling robust and safe machine learning pipelines through the assessment of data coherence and AI performance.

David Fernández-Narro, Pablo Ferri, Ángel Sánchez-García +2

Biomedical Data Science Lab, Instituto Universitario de Tecnologías de la Información y Comunicaciones, Universitat Politècnica de Valéncia, Camino de Vera s/n, Valencia 46022, España

Distribution Shift Detection Temporal Distribution Shift

May 24, 2026cs.LG

ROAR: Retrieval Opportunity-Aware Refinement for Zero-Shot Time Series Forecasting

Retrieval augmentation provides time series forecasters with historical continuations, yet even candidates that outperform the base forecast may fail to improve the final prediction. We propose ROAR, a Retrieval Opportunity-Aware Refinement framework for zero-shot time series forecasting. To better exploit these improvement opportunities, its training objective allocates additional emphasis across queries based on base-forecast difficulty and the relative improvement offered by retrieved candidates. Using this objective, ROAR first learns to aggregate aligned historical candidates and uses a learned gate to control their correction strength against a fixed base forecaster. It then jointly calibrates the forecasting module and gate to coordinate their contributions, while anchoring the combined prediction to the first-stage refined output. We derive exact decompositions of refinement gains and the opportunity-weighted training loss, and characterize additional gains from joint calibration under a local linearization. Experiments on seven benchmarks show that ROAR achieves the lowest average MSE among the compared methods. Further evaluations demonstrate average forecasting improvements across multiple backbone families and retrieval-augmented forecasters.

Jinjin Chi, Lei Feng, Yiming Wang +4

College of Computer Science and Technology, Jilin University, Changchun, China · College of Computing and Data Science, Nanyang Technological University, Singapore

Zero-Shot Time Series Forecasting Time Series Forecasting OOD Generalization Time Series Decomposition Invariant Representation Learning Retrieval-Augmented Time Series Forecasting+2

May 23, 2026cs.CL

Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions

Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tuning four transformer encoders -- XLM-RoBERTa (base and large) and their legal-domain variants -- on Ukrainian court decisions from three temporal epochs defined by geopolitical disruptions: pre-war (2008-2013), hybrid war (2014-2021), and full-scale invasion (2022-2026). Each model is trained on one epoch and evaluated on all three, producing a 3x3 cross-temporal generalization matrix. Four findings emerge. (1) Forward degradation is severe: models trained on pre-war data lose up to 27.2 percentage points of macro-F1 when applied to full-scale invasion era decisions. (2) The degradation is asymmetric: backward transfer (full-scale to pre-war) is substantially more robust than forward transfer, consistent with the hypothesis that legal language is additive. (3) Legal-domain pretraining (Legal-XLM-R) does not improve absolute performance but reduces forward degradation magnitude and asymmetry. (4) Chronological continual learning eliminates catastrophic forgetting for general XLM-R: pre-war knowledge is fully retained (+1.8 to +6.2 pp) while full-scale performance gains +16.5 to +19.0 pp; reverse-chronological training causes severe forgetting. Cross-jurisdictional pretraining on Swiss Judgment Prediction data improves absolute performance but does not reduce temporal degradation magnitude, confirming that temporal drift is an intrinsic property of legal language evolution. The dataset (428K decisions across three epochs) is publicly available as a LEXTREME contribution.

Volodymyr Ovcharov

Language Model Pretraining Legal NLP Distribution Shift Legal Judgment Prediction Continual Learning Temporal Distribution Shift

May 20, 2026cs.LG

Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting

Non-stationary time series forecasting is challenged by evolving distribution shifts that static models struggle to capture. While Mixture-of-Experts (MoE) architectures offer a promising paradigm for decoupling complex drift patterns, existing approaches are limited by fixed expert pools and memoryless routing, hampering their ability to adapt to abrupt regime shifts. To address this, we propose Dynamic TMoE, a framework that unifies architectural evolution with temporal continuity during learning phase. By detecting distribution shifts via Maximum Mean Discrepancy (MMD), we dynamically instantiate heterogeneous experts and prune redundant ones to optimize capacity. Additionally, a temporal memory router leverages recurrent states and an anomaly repository to ensure stable, context-aware expert selection without requiring test-time updates. Experiments on nine benchmarks demonstrate state-of-the-art performance, reducing MSE by 10.4% and MAE by 7.8%. Code is available at https://github.com/andone-07/Dynamic-TMoE.

Jiawen Zhu, Shuhan Liu, Di Weng +1

School of Software Technology, Zhejiang University, Ningbo, China · State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China

Concept Drift Mixture of Experts Non-Stationary Time Series Forecasting Mixture-of-Experts Models Temporal Distribution Shift

May 19, 2026cs.LG

DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift

We introduce DeRegiME -- Deep Regime Mixture of Experts -- a direct multi-horizon probabilistic forecaster that separates latent uncertainty regimes from the underlying signal and softly assigns each forecast location to learned recurring regimes using a sparse variational Gaussian process (GP) whose nonstationary regime-mixing kernel and Student-t likelihood combine per-regime sub-kernels and noise processes via a shared gate. This yields a single sparse-GP posterior, not a mixture of GP experts. DeRegiME addresses a key limitation of neural forecasters: point forecasts discard residual uncertainty, and probabilistic heads -- whether single marginals, uninterpreted mixtures, quantile sets, or diffusion samples -- rarely expose the regime structure of the residual. Yet distribution shift in noisy heteroskedastic time series may be abrupt, gradual, or horizon-dependent and often appears in residual uncertainty rather than the conditional mean. DeRegiME yields an interpretable mean-residual-noise decomposition with a direct-sum feature-space representation that anchors regimes as clusters of residual similarity whose transitions surface as implicit changepoints. The effective number of regimes is pruned by the stick-breaking gate. We prove kernel validity and predictive-density propriety, and across ten benchmarks and three encoder grids DeRegiME improves negative log predictive density (NLPD) by 20.3% over the strongest encoder-matched baseline, a DeepAR/GluonTS-style dynamic Student-t head, with parallel gains on CRPS (3.0%) and MSE (4.7%). Improvements are consistent across all datasets, which span abrupt, gradual, and seasonal shifts.

Kieran Wood, Stefan Zohren, Stephen J. Roberts

Machine Learning Research Group, University of Oxford · Oxford-Man Institute, University of Oxford

Distribution Shift Robustness Time Series Forecasting Non-Stationary Time Series Forecasting Probabilistic Time Series Forecasting Temporal Distribution Shift Gaussian Process Regression

May 18, 2026cs.LG

L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting

Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to the future in the observation space to fit value-level dependencies. However, real-world systems often undergo distribution shifts and regime changes. In such cases, a unified mapping can exhibit response lag around turning points, causing error accumulation within the switching window and reducing forecasting reliability. To address this issue, we propose L-Drive, a change-aware forecasting framework. L-Drive introduces a Latent-Context, to explicitly characterize high-level dynamics evolving over time, and uses gating to modulate increment representations. This provides more timely change cues and improves adaptation to changing segments. In addition, it incorporates patch-shared relative positional basis functions to strengthen intra-segment structural modeling and reduce overfitting caused by absolute-position memorization. Extensive experiments validate the effectiveness of L-Drive and show a better overall trade-off between forecasting accuracy and computational efficiency.

Fan Zhang, Shijun Chen, Hua Wang

Shandong Technology and Business University, Yantai, Shandong, China · Ludong University, Yantai, Shandong, China

Multivariate Time Series Forecasting Latent Dynamics Modeling Time Series Forecasting Non-Stationary Time Series Forecasting Temporal Distribution Shift

May 15, 2026cs.LG

Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix

Transformer-based architectures have become the dominant paradigm for Continuous-Time Dynamic Graph (CTDG) learning, yet their performance remains limited on temporally shifted datasets. In this work, we identify attention dispersion as a shared failure mode of dynamic graph Transformers under temporal distribution shift. Through controlled ablation contrasting structurally and temporally distinguished historical neighbors against random ones, we show that prediction depends on a class of critical nodes that carry consistently more predictive signal than arbitrary neighbors. However, existing Transformers fail to focus on these nodes even when they are present in the input, as temporal shift weakens attention contrast and produces overly dispersed attention distributions. This diagnosis suggests a simple and transferable fix: replace standard attention with differential attention, which suppresses common-mode attention and amplifies distinctive token-level signals. When added to three representative CTDG Transformer baselines, differential attention consistently improves performance, with gains concentrated on high-shift datasets. Attention-level measurements further confirm the mechanism, showing reduced attention entropy and increased attention mass on critical nodes. Building on these findings, we introduce DiffDyG, a reference implementation combining differential attention with standard input encodings. Across 9 benchmarks and three negative sampling protocols, DiffDyG achieves SOTA performance, with especially large gains on the most shifted datasets.

Jinhao Zhang, Kangfei Zhao, Qiuhao Zeng +1

Beijing Institute of Technology · University of Toronto · Hong Kong Baptist University

Distribution Shift Robustness Temporal GNNs Dynamic Graph Learning Attention Mechanisms Temporal Distribution Shift

May 8, 2026cs.LG

STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecasting

Test-Time Adaptation (TTA) aims to improve time series forecasting under distribution shifts by using limited observations revealed during inference. However, forecasting TTA must operate in a source-free online setting, where the adaptation signal is short, temporally correlated, and potentially noisy. Existing methods can therefore suffer from weak identifiability, error accumulation, and unstable long-horizon corrections when the revealed prefix is sparse or contaminated. To address these issues, we propose STEPS, a Smooth Temporal Error Propagation Solver for TTA in time-series forecasting. STEPS reformulates forecasting TTA as a Dirichlet Boundary Value Problem on a temporal manifold, where the revealed prefix error serves as the boundary condition for the unknown future error field. Then, STEPS solves a smooth and bounded correction field in prediction space: a Local Solver propagates prefix errors under temporal smoothness, a Global Solver retrieves stable cross-window error memory and Spatiotemporal Manifold Fusion (SMF) integrates both solutions into the final correction. Across six standard benchmarks and four frozen backbones, STEPS achieves an average relative MSE reduction of 26.82% over the zero-shot backbone, exceeding the strongest compared TTA baseline by 12.77%. Additional sparse prefix and contamination tests confirm the robustness of STEPS under limited and noisy prefixes.

Jiaqi Liu, Yifan Ouyang, Zhifei Song +2

School of Artificial Intelligence and Robotics, Xiamen University Malaysia · S.M.A.R.T. NEXUS Centre of Excellence, Xiamen University Malaysia Sepang, Selangor 43900, Malaysia

Source-Free Domain Adaptation Test-Time Adaptation Time Series Forecasting Non-Stationary Time Series Forecasting Temporal Distribution Shift

May 8, 2026cs.LG

PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift

Scientific foundation models are expected to reuse representations under changes in dataset, acquisition protocol, and deployment domain, yet many sequence backbones treat scientific temporal structure as an unconstrained pattern to be fitted. We argue that this misses a central property of natural dynamical systems: neural and atmospheric time series are organized by interacting processes across multiple physical timescales, and failure to preserve this multiscale structure contributes to brittleness under distribution shift. We formalize this failure mode as temporal kernel mismatch, where a model fits in-distribution dynamics with an effective memory policy that is not anchored to the signal's physical timescales, leading to representation drift and degraded transfer. We propose Physics-Informed Multi-Scale Mamba (PIMSM), a state-space architecture that maps spectrum-estimated transition points between frequency regimes (knee frequencies) to scale-specific discretization parameters and anchors them to acquisition time units. On Human Connectome Project fMRI, PIMSM improves robustness and representation stability under severe temporal-context truncation, extreme low-resource transfer, and resting-state-to-task-state generalization. Without modality-specific adaptation, the same architecture also attains the lowest variable-wise MAE across all reported horizons and variables on Weather-5K held-out-station spatial out-of-distribution forecasting. These results support temporal-scale alignment as a practical inductive bias for scientific foundation models that must preserve structure, not only fit correlations, under deployment shift.

Sangyoon Bae, Shinjae Yoo, Jiook Cha

Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul, South Korea, 08826 · Department of Psychology Seoul National University Seoul, South Korea, 08826

Domain Generalization Physics-Informed ML Time Series Representation Learning Time-Series Foundation Models Multiscale Time-Series Modeling Temporal Distribution Shift+1

May 7, 2026cs.LG

Hedging Memory Horizons for Non-Stationary Prediction via Online Aggregation

We study online prediction under distribution shift, where inputs arrive chronologically and outcomes are revealed only after prediction. In this setting, predictors must remain stable in quiet regimes yet adapt when regimes shift, and the right adaptation memory is unknown in advance. We propose MELO (Memory-hedged Exponentially Weighted Least-Squares Online aggregation), a model-agnostic method that hedges across adaptation scales: it wraps any non-anticipating base-predictor pool with exponentially weighted least-squares (EWLS) adaptation experts at multiple forgetting factors, and aggregates raw and EWLS-adapted forecasts with MLpol, a parameter-free online aggregation rule. Under boundedness conditions, we establish deterministic oracle inequalities showing that it competes with both the best raw predictor and the best bounded, time-varying affine combinations of the base predictions, up to a path-length-dependent tracking cost and a sublinear aggregation overhead. We evaluate MELO on French national electricity-load forecasting through the COVID-19 lockdown using no regime indicators, lockdown dates, or policy covariates. MELO reduces overall RMSE by 34.7% relative to base-only MLpol and achieves lower overall RMSE than a TabICL reference supplied with an external COVID policy-response covariate. Moreover, MELO requires only lightweight per-step recursive updates without model retraining.

Yutong Wang, Yannig Goude, Qiwei Yao

Department of Statistics, LSE · Électricité de France R&D

Ensemble Learning Time Series Forecasting Non-Stationary Time Series Forecasting Electricity Load Forecasting Adaptive Learning Temporal Distribution Shift

May 1, 2026cs.LG

PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting

Real-world time series forecasting faces the fundamental challenge of non-stationary statistical properties, including shifts in mean and variance over time. While reversible instance normalization (RevIN) has shown promise by stationarizing inputs and denormalizing outputs, it relies on the strong assumption that historical and future distributions remain identical. We observe that in many practical applications, distribution shifts follow cyclical patterns that correlate with periodic positions (e.g., seasonal and holiday volatility). To this end, we propose PAMod, a lightweight yet powerful framework that models cyclical distribution shifts via Phase-Amplitude Modulation in the normalized feature space. PAMod learns periodic embeddings to modulate representations: phase modulation captures mean shifts, while amplitude modulation adapts to variance changes. Crucially, we prove mathematically that modulating in normalized space is equivalent to applying dynamic denormalization, offering an elegant unification of distribution adaptation and representation learning. Extensive experiments on twelve real-world benchmarks demonstrate that PAMod achieves state-of-the-art performance with fewer computational resources. Furthermore, our modulation mechanism, as a novel plug-and-play technique, can improve existing time-series forecasting methods with simple integration.

Yingbo Zhou, Yutong Ye, Shuhao Li +5

Fudan University · Beihang University · Beijing University of Posts and Telecommunications

Distribution Shift Time Series Forecasting Non-Stationary Time Series Forecasting Non-Stationary Time Series Temporal Distribution Shift

May 1, 2026cs.LG

Optimal Spatio-Temporal Decoupling for Bayesian Conformal Prediction

Online conformal prediction must balance fast adaptation to distribution shift against stable coverage: feedback-driven methods react quickly but become volatile, while strongly discounted Bayesian methods lag and inflate intervals at tight coverage. We introduce \textbf{State-Adaptive Bayesian Conformal Prediction (SA-BCP)}, which forms the predictive quantile as a gated convex combination of long-term temporal inertia and local spatial evidence from a kernel density estimate, controlled by a single interpretable evidence threshold

K

. We establish three results: (i) asymptotic marginal validity of the resulting intervals up to a gate-controlled bias that vanishes as spatial evidence accumulates (exact under recurrent states); (ii) a closed-form expression for the MSE-optimal threshold,

K^*_{\mathrm{MSE}}=α(1-α)/M^{\mathcal{T}}

, trading the coverage-indicator (Bernoulli) variance against the temporal structural bias

M^{\mathcal{T}}

; and (iii) a rolling-origin procedure for selecting

K

online -- consistent under stationarity, with

O(\sqrt{T\log N})

regret against the best fixed

K

and, for a segmented variant, a sublinear dynamic-regret bound under sublinearly many (

B_T=o(T)

) threshold shifts. Across four financial-volatility and weather datasets, three target coverage levels, and eight baselines, SA-BCP attains at-or-above-nominal coverage in most settings while producing substantially sharper intervals -- up to roughly

3\times

lower Winkler score than discounted Bayesian CP at the tightest coverage -- and a coverage-matched audit confirms these efficiency gains are not an artifact of under-coverage. We disclose our principal limitation: a volatility-specialized CF-GARCH competitor remains more efficient on its home volatility-base series, though it does not transfer across domains.

Yu-Hsueh Fang, Chia-Yen Lee

Department of Information Management, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Da’an Dist., Taipei, 106216, Taiwan.

Conformal Prediction Temporal Distribution Shift Regression Prediction Intervals