Elastic Weight Consolidation

Also known as EWC

Ask about this topic

Overview

EWC estimates parameter importance, commonly with diagonal Fisher information, and penalizes changes to important weights as a model learns a new task. Researchers combine it with replay, low-rank fine-tuning, adaptive or layer-wise penalties, and curvature-aware estimates in settings from vision and speech to language and multimodal models. Benchmarks typically measure performance on new tasks alongside forgetting or backward transfer, and EWC can help retain prior capabilities during sequential adaptation. Its central tension is stability versus plasticity: importance estimates can be inaccurate and fixed penalties can hinder adaptation, so when to regularize and how to set the strength remain open questions.

Latest papers

CardsList

17 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Beyond Parameter Protection: Fisher-Shaped EWC for Replay-Free Continual Learning

    Oct 27, 2026Liying Wang, Simone Magistri, Joost van de WeijerElastic Weight ConsolidationRegularization-Based Continual Learning

    Department of Computer Science, Universitat Aut`onoma de Barcelona, Spain · Computer Vision Center, Barcelona, Spain · Media Integration and Communication Center, University of Florence, Italy

  2. Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR

    Oct 9, 2026Thai Quoc On, Homayoon BeigiKronecker-Factored ApproximationElastic Weight Consolidation

    Department of Computer Science Columbia University, NYC, NY, USA · Mechanical Engineering Dept. and Electrical Engineering Dept. Columbia University, NYC, NY, USA · and Recognition Technologies, Inc. South Salem, NY, USA

  3. Towards Eliminating Catastrophic Forgetting in the Curriculum Learning of Math Reasoning Tasks

    Sep 27, 2026Zengyan Yang, Yangyang Wu, Kai Huang +3Elastic Weight ConsolidationMathematical Reasoning

    Zhejiang University · Ant Group

  4. Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

    Sep 23, 2026Niklas Scholz, David Thulke, Abdallah Nasir +3LLM Fine-TuningElastic Weight Consolidation

    AppTek GmbH, Aachen, Germany · Machine Learning and Human Language Technology, RWTH Aachen University, Germany · Applied Science Private University, Amman, Jordan

  5. The Sequential Price of Continual Learning

    Aug 30, 2026Zonghuan Xu, Xingjun MaContinual LearningElastic Weight Consolidation

    Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China · Shanghai Key Laboratory of Multimodal Embodied AI, Shanghai, China

  6. Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive

    Aug 16, 2026Brian B. Moser, Ahmed Anwar, Tobias Christian Nauen +5Regularization-Based Continual LearningContinual Learning

    German Research Center for Artificial Intelligence (DFKI) · RPTU University Kaiserslautern-Landau

  7. An active-learning framework for real-time depth perception from monocular vision streams

    Aug 5, 2026Xiaorong Zeng, Weiqiang Chen, Peng Shi +4Edge InferenceMonocular Depth Estimation

    School of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen, Fujian 361024, China · King Long United Automotive Industry Co. Ltd., Xiamen 361023, China · School of Electrical and Electronic Engineering, The University of Adelaide, Adelaide, SA 5005, Australia +2

  8. Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning

    Jul 13, 2026Jing Liu, Chenxuanyin Zou, Jiayang Ren +5Multimodal Federated LearningGenerative Replay

    Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC V6T 1Z4, Canada · College of Future Information Technology, Fudan University, Shanghai 200433, China · Department of Chemical and Biological Engineering, The University of British Columbia, Vancouver, BC V6T 1Z4, Canada +3

  9. RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models

    Jun 22, 2026Ulas Berk Karli, Tesca FitzgeraldContinual Robot LearningRobot Skill Learning

    Department of Computer Science Yale University United States

  10. CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift

    Jun 22, 2026Amrita Singh, Rishabh JhaVLM AdaptationElastic Weight Consolidation

    Mindriser’s Consortium, Kathmandu, Nepal · University of Victoria, BC, Canada

  11. Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention

    May 12, 2026Hamza Ahmed Durrani, Rafay Suleman DurraniVision-Language ModelsCross-Modal Alignment

    Sejong University, Computer Science Engineering · Technische Universität Ilmenau, Computer Engineering

  12. Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I Backdoors

    May 8, 2026Lu Bowen, Xinyu Tang, Yin Yin Low +1Backdoor AttacksElastic Weight Consolidation

    Monash University

  13. MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC

    May 4, 2026Joern HentschStability-Plasticity DilemmaDynamic Neural Networks

  14. Non-Equilibrium Stochastic Dynamics as a Unified Framework for Insight and Repetitive Learning: A Kramers Escape Approach to Continual Learning

    Apr 5, 2026Gunn KimContinual LearningStability-Plasticity Dilemma

    Department of Physics, Sejong University, Seoul 05006, Republic of Korea

  15. Elastic Weight Consolidation Done Right for Continual Learning

    Mar 19, 2026Xuan Liu, Xiaobin ChangRegularization-Based Continual LearningContinual Learning

    School of Artificial Intelligence, Sun Yat-sen University, China · Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Ministry of Culture and Tourism, Sun Yat-sen University · Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China

  16. Revisiting Weight Regularization for Low-Rank Continual Learning

    Feb 19, 2026Yaoyue Zheng, Yin Zhang, Joost van de Weijer +4Incremental LearningElastic Weight Consolidation

    State Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Shaanxi, China · Computer Vision Center, Barcelona, Spain · Universitat Aut`onoma de Barcelona, Barcelona, Spain +3

  17. DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised

    Nov 13, 2023Abanoub Ghobrial, Kerstin EderTest-Time AdaptationUnsupervised Domain Adaptation

    University of Bristol, Bristol, UK