IDER: IDempotent Experience Replay for Reliable Continual Learning

• URL: http://arxiv.org/abs/2603.00624v2
• Date: Tue, 03 Mar 2026 06:15:08 GMT
• Title: IDER: IDempotent Experience Replay for Reliable Continual Learning
• Authors: Zhanwang Liu, Yuting Li, Haoyuan Gao, Yexin Li, Linghe Kong, Lichao Sun, Weiran Huang,
• Abstract summary: Catastrophic forgetting is a major challenge in continual learning (CL)<n>Existing uncertainty-aware CL methods suffer from high computational overhead and incompatibility with mainstream replay methods.<n>We propose idempotent experience replay (IDER), a novel approach based on the idempotent property where repeated function applications yield the same output.
• Score: 36.35747221992653
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and shown to reduce forgetting. Furthermore, CL models deployed in mission-critical settings can benefit from uncertainty awareness by calibrating their predictions to reliably assess their confidences. However, existing uncertainty-aware continual learning methods suffer from high computational overhead and incompatibility with mainstream replay methods. To address this, we propose idempotent experience replay (IDER), a novel approach based on the idempotent property where repeated function applications yield the same output. Specifically, we first adapt the training loss to make model idempotent on current data streams. In addition, we introduce an idempotence distillation loss. We feed the output of the current model back into the old checkpoint and then minimize the distance between this reprocessed output and the original output of the current model. This yields a simple and effective new baseline for building reliable continual learners, which can be seamlessly integrated with other CL approaches. Extensive experiments on different CL benchmarks demonstrate that IDER consistently improves prediction reliability while simultaneously boosting accuracy and reducing forgetting. Our results suggest the potential of idempotence as a promising principle for deploying efficient and trustworthy continual learning systems in real-world applications.Our code is available at https://github.com/YutingLi0606/Idempotent-Continual-Learning.

Related papers

• Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning [51.07663354001582]
  Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task.<n>We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches.<n>We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods.
  arXiv  Detail & Related papers  (2025-12-01T15:56:00Z)
• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning [0.0]
  We introduce DQInit, a method that adapts value function initialization to deep reinforcement learning.<n>DQInit reuses compact Q-values extracted from previously solved tasks as a transferable knowledge base.<n>It employs a knownness-based mechanism to softly integrate these transferred values into underexplored regions and gradually shift toward the agent's learned estimates.
  arXiv  Detail & Related papers  (2025-08-12T18:32:08Z)
• ACU: Analytic Continual Unlearning for Efficient and Exact Forgetting with Privacy Preservation [39.0731790601695]
  Continual Unlearning (CU) aims to sequentially forget particular knowledge acquired during the Continual Learning phase.<n>Most existing unlearning methods require access to the retained dataset for re-training or fine-tuning.<n>We propose a novel gradient-free method for CU, named Analytic Continual Unlearning (ACU), for efficient and exact forgetting with historical data privacy preservation.
  arXiv  Detail & Related papers  (2025-05-18T05:28:18Z)
• CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous Driving [0.0]
  End-to-end vision-based imitation learning has demonstrated promising results in autonomous driving.<n>Traditional approaches rely on either regressionbased models, which provide precise control but lack confidence estimation, or classification-based models, which offer confidence scores but suffer from reduced precision due to discretization.<n>We introduce a dual-head neural network architecture that integrates both regression and classification heads to improve decision reliability in imitation learning.
  arXiv  Detail & Related papers  (2025-03-02T08:19:02Z)
• Accurate Forgetting for Heterogeneous Federated Continual Learning [89.08735771893608]
  We propose a new concept accurate forgetting (AF) and develop a novel generative-replay methodMethodwhich selectively utilizes previous knowledge in federated networks.<n>We employ a probabilistic framework based on a normalizing flow model to quantify the credibility of previous knowledge.
  arXiv  Detail & Related papers  (2025-02-20T02:35:17Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)
• Temporal-Difference Variational Continual Learning [77.92320830700797]
  We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.<n>Our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• CBA: Improving Online Continual Learning via Continual Bias Adaptor [44.1816716207484]
  We propose a Continual Bias Adaptor to augment the classifier network to adapt to catastrophic distribution change during training. In the testing stage, CBA can be removed which introduces no additional cost and memory overhead. We theoretically reveal the reason why the proposed method can effectively alleviate catastrophic distribution shifts.
  arXiv  Detail & Related papers  (2023-08-14T04:03:51Z)
• Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning [73.24988226158497]
  We consider the high-impact problem of Data-Free Class-Incremental Learning (DFCIL) We propose a novel incremental distillation strategy for DFCIL, contributing a modified cross-entropy training and importance-weighted feature distillation. Our method results in up to a 25.1% increase in final task accuracy (absolute difference) compared to SOTA DFCIL methods for common class-incremental benchmarks.
  arXiv  Detail & Related papers  (2021-06-17T17:56:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.