The Anatomy and Boundary of Adaptation under Temporal Tabular Shift

Tabular model performance degrades when feature distributions change over time or the relationship between features and outcome variables change over time, known as data drift and concept drift, respectively. These issues are challenging to mitigate in real time because labeled data may not be immediately available, or re-training a model could be impractical. While tools exist to reduce drift, they are typically bespoke to neural network architectures and adapt how models are trained. In this paper, we offer an alternative post-hoc method to reduce concept drift, which is applicable to a variety of models, from trees to neural networks to tabular foundation models. This new tool is especially useful when constraints, such as high model accuracy, bounded inference time, or model size requires users to choose between different models for their specific use-cases. Our algorithm fits the base model separately on each labeled training period, measures how its parameters evolve against a single anchor model pooled over all of those periods, compresses those changes with a low-rank factorization, and extrapolates each latent factor forward with a damped, regularized forecast. On the 18-dataset Drift-Resilient TabPFN benchmark, evaluated under that benchmark's own protocol and metric, the extrapolation improves every base family it is applied to, and achieves performance competitive with the state-of-the-art Drift-Resilient TabPFN with seconds of training. In contrast, Drift-Resilient TabPFN requires pre-training on millions of synthetic datasets over approximately 1,300 GPU-hours, and is orders of magnitude slower in inference (depending on the model). In the discussion, we explore the promise and challenges of extending this tool to other modalities.

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.

Tabular data is used extensively in many real-world use cases. Deep learning models have been developed to deal with tabular data, but generally perform poorly when the test data distribution differs from that of the training data. Researchers have proposed test-time adaptation approaches to deal with this problem. The fully test-time adaptation (FTTA) setting involves adapting deployed classifiers to shifted target distributions using only unlabeled test data. Leading FTTA methods inherit a batch-dependent approach from computer vision literature. This paper demonstrates for the first time that such approaches degrade sharply in strict streaming regimes where examples arrive and must be classified one at a time. This occurs because at a batch size of one, batch-level statistics become unavailable or poorly estimated. We argue that singleton tabular FTTA is not merely a small-batch variant of ordinary FTTA, but a distinct identifiability problem where only the location of the model's score stream remains directly observable. To address this, we propose Prequential Logit-Origin Centering (PLOC), a lightweight approach that keeps the source model frozen and shifts the logit space at each step. PLOC stores only a single running number (the mean of past logits), requires no labels, estimates no priors, and bypasses weight updates entirely. A deferred variant applies a static shift that preserves the source ranking, and thus the AUROC, exactly. Evaluated across five tabular benchmarks, three architectures (MLP, FT-Transformer, and TabTransformer), and five independent source checkpoints, PLOC significantly outperforms strong tabular and entropy-based baselines.