Online Continual Learning

Ask about this topic

Overview

Online continual learning studies how models can learn from data as it arrives, often in a single pass and without known task boundaries, while retaining useful information from the past. Common approaches use replay buffers or structured memories, constrain updates with regularization or parameter-efficient adapters, expand model capacity, or detect distribution shifts to trigger targeted updates. Researchers evaluate these methods on streaming vision and language tasks, time-series drift, robotics, and resource-constrained devices, measuring accuracy, forgetting, transfer, memory, and compute. A central challenge is balancing adaptation to new or recurring patterns against retention, while ensuring results hold under realistic streams and do not depend on hidden assumptions such as task labels or pretrained features.

Latest papers

CardsList

106 papers18 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Mar 9, 2026

TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery

On-the-fly category discovery (OCD) aims to recognize known categories while simultaneously discovering novel ones from an unlabeled online stream, using a model trained only on labeled data. Existing approaches freeze the feature extractor trained offline and employ a hash-based framework that quantizes features into binary codes as class prototypes. However, discovering novel categories with a fixed knowledge base is counterintuitive, as the learning potential of incoming data is entirely neglected. In addition, feature quantization introduces information loss, diminishes representational expressiveness, and amplifies intra-class variance. It often results in category explosion, where a single class is fragmented into multiple pseudo-classes. To overcome these limitations, we propose a test-time adaptation framework that enables learning through discovery. It incorporates two complementary strategies: a semantic-aware prototype update and a stable test-time encoder update. The former dynamically refines class prototypes to enhance classification, whereas the latter integrates new information directly into the parameter space. Together, these components allow the model to continuously expand its knowledge base with newly encountered samples. Furthermore, we introduce a margin-aware logit calibration in the offline stage to enlarge inter-class margins and improve intra-class compactness, thereby reserving embedding space for future class discovery. Experiments on standard OCD benchmarks demonstrate that our method substantially outperforms existing hash-based state-of-the-art approaches, yielding notable improvements in novel-class accuracy and effectively mitigating category explosion. The code is publicly available at \textcolor{blue}{https://github.com/ynanwu/TALON}.

Yanan Wu, Yuhan Yan, Tailai Chen +5

College of Information and Electrical Engineering, China Agricultural University, China · College of Science, China Agricultural University, China · Woof RoboT Co., Ltd., China +4

Test-Time AdaptationPrototype-Based ClassificationOnline Continual Learning
AskPDF
Mar 8, 2026

Online Continual Learning for Anomaly Detection in IoT under Data Distribution Shifts

In this work, we present OCLADS, a novel communication framework with continual learning (CL) for Internet of Things (IoT) anomaly detection (AD) when operating in non-stationary environments. As the statistical properties of the observed data change with time, the on-device inference model becomes obsolete, which necessitates strategic model updating. OCLADS keeps track of data distribution shifts to timely update the on-device IoT AD model. To do so, OCLADS introduces two mechanisms during the interaction between the resource-constrained IoT device and an edge server (ES): i) an intelligent sample selection mechanism at the device for data transmission, and ii) a distribution-shift detection mechanism at the ES for model updating. Experimental results with TinyML demonstrate that our proposed framework achieves high inference accuracy while realizing a significantly smaller number of model updates compared to the baseline schemes.

Matea Marinova, Shashi Raj Pandey, Junya Shiraishi +3

Faculty of Electrical Engineering and Information Technologies, Ss. Cyril and Methodius University in Skopje, 1000 Skopje, North Macedonia · Dept. of Electronic Systems, Aalborg University, Aalborg, Denmark

Continual Anomaly DetectionOnline Anomaly DetectionAnomaly DetectionOnline Continual LearningDistribution Shift Detection
AskPDF
Mar 8, 2026

Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgetting

Catastrophic forgetting remains a central challenge in continual learning (CL), yet lacks a unified information-theoretic explanation for why some architectures forget catastrophically while others do not. We introduce Context Channel Capacity (CctxC_\mathrm{ctx}), the mutual information between a CL architecture's context signal and its generated parameters, and prove that zero forgetting requires Cctx≥H(T)C_\mathrm{ctx} \geq H(T), where H(T)H(T) is the task identity entropy. We establish an Impossibility Triangle -- zero forgetting, online learning, and finite parameters cannot be simultaneously satisfied by sequential state-based learners -- and show that conditional regeneration architectures (HyperNetworks) bypass this triangle by redefining parameters as function values rather than states. We validate this framework across 8 CL methods on Split-MNIST (1,130+ experiments over 86 days, 4 seeds each), showing that CctxC_\mathrm{ctx} perfectly predicts forgetting behavior: methods with Cctx=0C_\mathrm{ctx} = 0 (NaiveSGD, EWC, SI, LwF, CFlow) exhibit catastrophic forgetting (6--97%), while methods with Cctx≈1C_\mathrm{ctx} \approx 1 (HyperNetwork) achieve zero forgetting (98.8% ACC). We further propose Wrong-Context Probing (P5), a practical diagnostic protocol for measuring CctxC_\mathrm{ctx}, and extend the framework to CIFAR-10 via a novel Gradient Context Encoder that closes the oracle gap from 23.3pp to 0.7pp. A systematic taxonomy of 15+ closed research directions -- including the Hebbian null result (frozen random features outperform learned features), CFlow's θ0θ_0-memorizer phenomenon, and the SNS_N symmetry barrier to column specialization -- provides the community with precisely diagnosed negative results. Our central design principle: architecture over algorithm -- the context pathway must be structurally unbypassable.

Ran Cheng

Catastrophic ForgettingOnline Continual Learning
AskPDF
Mar 8, 2026

Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams

LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We introduce Online Adaptation to Continual Knowledge Streams(OAKS) to evaluate this capability, establishing a benchmark for online adaptation over streaming, continually updating knowledge. Specifically, the benchmark is structured as a sequence of fine-grained context chunks where facts change dynamically across time intervals. OAKS comprises two datasets: OAKS-BABI and OAKS-Novel, where individual facts evolve multiple times across context chunks. These datasets include dense annotations to measure whether models track changes accurately. Evaluating 14 models with varied inference approaches, we observe significant limitations in current methodologies. Both state-of-the-art models and agentic memory systems fail to adapt robustly on OAKS, demonstrating delays in state-tracking and susceptibility to distraction within streaming environments.

Jiyeon Kim, Hyunji Lee, Dylan Zhou +6

KAIST AI · UNC Chapel Hill · Google +3

LLM EvaluationContinual Learning for LLMsOnline Continual LearningMemory-Augmented Language Models
AskPDF
Mar 4, 2026

When and Where to Reset Matters for Long-Term Test-Time Adaptation

When continual test-time adaptation (TTA) persists over the long term, errors accumulate in the model and further cause it to predict only a few classes for all inputs, a phenomenon known as model collapse. Recent studies have explored reset strategies that completely erase these accumulated errors. However, their periodic resets lead to suboptimal adaptation, as they occur independently of the actual risk of collapse. Moreover, their full resets cause catastrophic loss of knowledge acquired over time, even though such knowledge could be beneficial in the future. To this end, we propose (1) an Adaptive and Selective Reset (ASR) scheme that dynamically determines when and where to reset, (2) an importance-aware regularizer to recover essential knowledge lost due to reset, and (3) an on-the-fly adaptation adjustment scheme to enhance adaptability under challenging domain shifts. Extensive experiments across long-term TTA benchmarks demonstrate the effectiveness of our approach, particularly under challenging conditions. Our code is available at https://github.com/YonseiML/asr.

Taejun Lim, Joong-Won Hwang, Kibok Lee

1Yonsei University · 2ETRI

Test-Time AdaptationContinual Test-Time AdaptationModel CollapseOnline Continual Learning
AskPDF
Mar 3, 2026

cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series

Dealing with an unbounded data stream involves overcoming the assumption that data is identically distributed and independent. A data stream can, in fact, exhibit temporal dependencies (i.e., be a time series), and data can change distribution over time (concept drift). The two problems are deeply discussed, and existing solutions address them separately: a joint solution is absent. In addition, learning multiple concepts implies remembering the past (a.k.a. avoiding catastrophic forgetting in Neural Networks' terminology). This work proposes Continuous Progressive Neural Networks (cPNN), a solution that tames concept drifts, handles temporal dependencies, and bypasses catastrophic forgetting. cPNN is a continuous version of Progressive Neural Networks, a methodology for remembering old concepts and transferring past knowledge to fit the new concepts quickly. We base our method on Recurrent Neural Networks and exploit the Stochastic Gradient Descent applied to data streams with temporal dependencies. Results of an ablation study show a quick adaptation of cPNN to new concepts and robustness to drifts.

Federico Giannini, Giacomo Ziffer, Emanuele Della Valle

DEIB, Politecnico di Milano, Milano, Italy

Online Continual LearningConcept DriftCatastrophic Forgetting
AskPDF
Mar 2, 2026

Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments

Developing effective predictive models becomes challenging in dynamic environments that continuously produce data and constantly change. Continual Learning (CL) and Streaming Machine Learning (SML) are two research areas that tackle this arduous task. We put forward a unified setting that harnesses the benefits of both CL and SML: their ability to quickly adapt to non-stationary data streams without forgetting previous knowledge. We refer to this setting as Streaming Continual Learning (SCL). SCL does not replace either CL or SML. Instead, it extends the techniques and approaches considered by both fields. We start by briefly describing CL and SML and unifying the languages of the two frameworks. We then present the key features of SCL. We finally highlight the importance of bridging the two communities to advance the field of intelligent systems.

Federico Giannini, Giacomo Ziffer, Andrea Cossu +1

DEIB, Politecnico di Milano, Milano, 20133, Italy · Computer Science Department, University of Pisa, Pisa, Italy

Continual LearningOnline Continual LearningStreaming Algorithms
AskPDF
Feb 27, 2026

FastODT: A tree-based framework for efficient continual learning

Machine learning models deployed in real-world settings must operate under evolving data distributions and constrained computational resources. This challenge is particularly acute in non-stationary domains such as energy time series, weather monitoring, and environmental sensing. To remain effective, models must support adaptability, continuous learning, and long-term knowledge retention. This paper introduces a oblivious tree-based model with Hoeffding bound controlling its growth. It seamlessly integrates rapid learning and inference with efficient memory management and robust knowledge preservation, thus allowing for online learning. Extensive experiments across energy and environmental sensing time-series benchmarks demonstrate that the proposed framework achieves performance competitive with, and in several cases surpassing, existing online and batch learning methods, while maintaining superior computational efficiency. Collectively, these results demonstrate that the proposed approach fulfills the core objectives of adaptability, continual updating, and efficient retraining without full model retraining. The framework provides a scalable and resource-aware foundation for deployment in real-world non-stationary environments where resources are constrained and sustained adaptation is essential.

Daniel Bretsko, Piotr Walas, Devashish Khulbe +3

Masaryk University, Brno, Czech Republic · Warsaw University of Technology, Warsaw, Poland · Mycroft Mind, Brno, Czech Republic +2

Online Continual LearningDecision Tree LearningMemory-Efficient Training
AskPDF
Feb 26, 2026

Unsupervised Continual Learning for Amortized Bayesian Inference

Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers from performance degradation under model misspecification. While self-consistency (SC) training on unlabeled empirical data can enhance network robustness, current approaches are limited to static, single-task settings and fail to handle sequentially arriving data or distribution shifts. We propose a continual learning framework for ABI that decouples simulation-based pre-training from unsupervised sequential SC fine-tuning on real-world data. To address the challenge of catastrophic forgetting, we introduce two adaptation strategies: (1) SC with episodic replay, utilizing a memory buffer of past observations, and (2) SC with elastic weight consolidation, which regularizes updates to preserve task-critical parameters. Across three diverse case studies, our methods significantly mitigate forgetting and yield posterior estimates that outperform standard simulation-based training, achieving estimates closer to MCMC reference, providing a viable path for trustworthy ABI across a range of different tasks.

Aayush Mishra, Šimon Kucharský, Paul-Christian Bürkner

Department of Statistics, TU Dortmund University, Germany

Amortized InferenceOnline Continual Learning
AskPDF
Feb 23, 2026

Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS

Deep neural networks (DNNs) have been increasingly explored for receiver design because they can handle complex environments without relying on explicit channel models. Nevertheless, because communication channels change rapidly, their distributions can shift over time, often making periodic retraining necessary. This paper proposes a zero-overhead online and continual learning framework for orthogonal frequency-division multiplexing (OFDM) neural receivers that directly detect the soft bits of received signals. Unlike conventional fine-tuning methods that rely on dedicated training intervals or full resource grids, our approach leverages existing demodulation reference signals (DMRS) to simultaneously enable signal demodulation and model adaptation. We introduce three pilot designs: fully randomized, hybrid, and additional pilots that flexibly support joint demodulation and learning. To accommodate these pilot designs, we develop two receiver architectures: (i) a parallel design that separates inference and fine-tuning for uninterrupted operation, and (ii) a forward-pass reusing design that reduces computational complexity. Simulation results show that the proposed method effectively tracks both slow and fast channel distribution variations without additional overhead, service interruption, or catastrophic performance degradation under distribution shift.

Mohanad Obeed, Ming Jian

Advanced Wireless Technology Lab, Huawei Technologies Canada Co. Ltd, ON K2K 3J1, Canada

Wireless CommunicationsOnline Continual Learning
AskPDF
Feb 23, 2026

Representation Stability in a Minimal Continual Learning Agent

Continual learning systems are increasingly deployed in environments where retraining or reset is infeasible, yet many approaches emphasize task performance rather than the evolution of internal representations over time. In this work, we study a minimal continual learning agent designed to isolate representational dynamics from architectural complexity and optimization objectives. The agent maintains a persistent state vector across executions and incrementally updates it as new textual data is introduced. We quantify representational change using cosine similarity between successive normalized state vectors and define a stability metric over time intervals. Longitudinal experiments across eight executions reveal a transition from an initial plastic regime to a stable representational regime under consistent input. A deliberately introduced semantic perturbation produces a bounded decrease in similarity, followed by recovery and restabilization under subsequent coherent input. These results demonstrate that meaningful stability plasticity tradeoffs can emerge in a minimal, stateful learning system without explicit regularization, replay, or architectural complexity. The work establishes a transparent empirical baseline for studying representational accumulation and adaptation in continual learning systems.

Vishnu Subramanian

AI/ML Computational Science Associate Manager, Accenture

Continual LearningLifelong Learning AgentsStability-Plasticity DilemmaRepresentation DriftOnline Continual Learning
AskPDF
Nov 11, 2025

Are Current Continual Learning Methods Truly Agnostic? Introducing OPRE, a Step Toward Agnostic Continual Learning

In order to achieve Continual Learning (CL), the problem of catastrophic forgetting, one that has plagued neural networks since their inception, must be overcome. The evaluation of continual learning methods relies on splitting a known homogeneous dataset and learning the associated tasks one after the other. We argue that most CL methods introduce a priori information about the data to come and cannot be considered agnostic. We exemplify this point with the case of methods relying on pretrained feature extractors, which are still used in CL. After showing that pretrained feature extractors imply a loss of generality with respect to the data that can be learned by the model, we then discuss other kinds of a priori information introduced in other CL methods. We then present the Online Patch Redundancy Eliminator (OPRE), an online dataset-compression algorithm that discards information through two explicit, input-space criteria. With a classifier that was randomly initialized at test time, OPRE's performance matches reported state-of-the-art online continual-learning methods on CIFAR 10 and CIFAR-100 without any pretrained feature extractor, and outperforms GDumb at an identical memory budget-while making only minimal and interpretable assumptions about the data to come. We frame these results as an empirical, information-theoretic perspective on continual learning.

Raphaël Bayle, Martial Mermillod, Robert M. French

Univ. Grenoble Alpes, Univ. Savoie Mont Blanc, CNRS, LPNC, Grenoble, France · LEAD-CNRS UMR 5022, U. de Bourgogne Europe, Dijon, France

Continual LearningCoreset SelectionOnline Continual LearningTask-Free Continual LearningCatastrophic Forgetting
AskPDF
Nov 3, 2025

Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network

Edge AI must adapt to new classes and shifting data within a tight power budget, but online continual learning (learning from each sample before the next arrives) is where conventional processors are least efficient: each small update pays a full dispatch at full power. We present CLP-SNN, a spiking architecture that recasts the Continually Learning Prototypes (CLP) algorithm as event-driven neural dynamics: a self-normalizing local rule replaces CLP's global renormalization, prototype allocation becomes novelty-triggered neurogenesis, and correctness-modulated plasticity becomes reward-gated per-neuron metaplasticity. Deployed on Intel Loihi 2 as the first online continual learner on that chip, rehearsal-free CLP-SNN matches Replay and SLDA on OpenLORIS at 1-shot; at 25-shot, it stays within 0.8 percentage points of Replay and 6.2 points below covariance-based SLDA. Each prediction-and-update step on extracted features completes on-chip in 0.33 ms at 0.05 mJ, 7.3x lower latency and 341x lower energy than Replay on a Jetson Orin Nano.

Elvin Hajizada, Danielle Rager, Timothy Shea +5

Institute of Informatics, University of Munich (LMU), Munich, Germany · Intel Labs, Intel Corporation, Santa Clara, CA, USA · Southwest Research Institute, San Antonio, TX, USA +3

Online Continual LearningIncremental LearningOn-Device TrainingSpiking Neural NetworksNeuromorphic Computing
AskPDF
Oct 13, 2025

Local Timescale Gates for Timescale-Robust Continual Spiking Neural Networks

Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory, especially in continual learning. We propose Local Timescale Gating (LT-Gate), a neuron model that combines dual time-constant dynamics with an adaptive gating mechanism. Each spiking neuron tracks information on a fast and a slow timescale in parallel, and a learned gate locally adjusts their influence. This design enables individual neurons to preserve slow contextual information while responding to fast signals, addressing the stability-plasticity dilemma. We further introduce a variance-tracking regularization that stabilizes firing activity, inspired by biological homeostasis. Empirically, LT-Gate yields significantly improved accuracy and retention in sequential learning tasks: on a challenging temporal classification benchmark it achieves about 51 percent final accuracy, compared to about 46 percent for a recent Hebbian continual-learning baseline and lower for prior SNN methods. Unlike approaches that require external replay or expensive orthogonalizations, LT-Gate operates with local updates and is fully compatible with neuromorphic hardware. In particular, it leverages features of Intel's Loihi chip (multiple synaptic traces with different decay rates) for on-chip learning. Our results demonstrate that multi-timescale gating can substantially enhance continual learning in SNNs, narrowing the gap between spiking and conventional deep networks on lifelong-learning tasks.

Devansh Deep, Ansh Tiwari, Ayush Chauhan

Spiking Neural NetworksOnline Continual LearningNeuromorphic Computing
AskPDF
Jun 12, 2025

TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree

Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially. This necessitates continual learning (CL) to update models online, enabling adaptation to new tasks while preserving past knowledge to prevent catastrophic forgetting. Nowadays, with the flourish of large pre-trained models (LPMs), efficiency has become increasingly critical for CL, due to their substantial computational demands and growing parameter sizes. In this paper, we introduce TreeLoRA (K-D Tree of Low-Rank Adapters), a novel approach that constructs layer-wise adapters by leveraging hierarchical gradient similarity to enable efficient CL, particularly for LPMs. To reduce the computational burden of task similarity estimation, we employ bandit techniques to develop an algorithm based on lower confidence bounds to efficiently explore the task structure. Furthermore, we use sparse gradient updates to facilitate parameter optimization, making the approach better suited for LPMs. Theoretical analysis is provided to justify the rationale behind our approach, and experiments on both vision transformers (ViTs) and large language models (LLMs) demonstrate the effectiveness and efficiency of our approach across various domains, including vision and natural language processing tasks.

Yu-Yang Qian, Yuan-Ze Xu, Zhen-Yu Zhang +2

National Key Laboratory for Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · RIKEN AIP, Tokyo, Japan

Continual Learning for LLMsLow-Rank AdaptationOnline Continual LearningIncremental LearningParameter-Efficient Fine-Tuning
AskPDF
Aug 19, 2024

AIR: Analytic Imbalance Rectifier for Continual Learning

Continual learning (CL) agents incrementally learn from sequentially arriving data and adapt to the dynamic, ever-changing nature of real-world environments. However, many existing CL methods suffer performance degradation in evolving, imbalanced data streams due to limited adaptation to changing class frequencies or ineffective use of mixed data from new and previously observed classes. To deal with these challenges, we propose an analytic imbalance rectifier (AIR) algorithm for real-world CL. AIR is an online exemplar-free approach with a frozen backbone as the feature extractor and a closed-form incremental classifier whose weight equals the joint-learning weight for the same class-weighted ridge objective. AIR addresses class imbalance with an analytic reweighting module (ARM) that calculates a reweighting factor for each class in the loss function to equalize total sample weights across classes. Under long-tailed class-incremental learning, AIR leads 28 baselines in aggregate accuracy and exemplar-free methods in aggregate macro F1, gaining 3.21% accuracy and 2.14% macro F1 over the respective strongest exemplar-free baselines. Under the Si-Blurry setting with recurring classes, AIR leads 15 exemplar-based and exemplar-free baselines, gaining 2.32% aggregate accuracy and 1.27% aggregate macro F1 over the strongest baseline. One-sided paired tests support positive mean absolute gains in these four comparisons (Holm-adjusted p<0.006).

Di Fang, Yinan Zhu, Zhiping Lin +3

School of Future Technology, South China University of Technology, Guangzhou, China · Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China

Class-Imbalanced LearningClass-Incremental LearningContinual LearningOnline Continual LearningIncremental Learning
AskPDF