Paper Detail

Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks

Victor Cook, Gilles Sassatelli, Thierry Gil, Mohamed Watfa, Marina Reyboz

arxiv Score 27.5

Published 2026-10-27 · First seen 2026-10-28

Research Track A · General AI

Abstract

Equilibrium Propagation (EqProp) offers a biologically grounded and hardware-aligned alternative to backpropagation for training Hopfield Networks. However, its behavior in continual learning settings remains largely unexplored. This work confronts catastrophic forgetting in EqProp-trained Hopfield Networks from the inside out, eliminating the need for external data buffers or architectural overhead that standard Experience Replay \textbf{(ER)} and Generative Replay \textbf{(Gen-Replay)} inevitably require. We introduce an Energy-Based Generative Replay strategy \textbf{(EB-Gen)} which exploits the intrinsic generative dynamics of Hopfield Networks, allowing a single model to act as both classifier and replay samples generator. Samples capturing past task knowledge are generated by relaxing a frozen copy of the network, enabling rehearsal solely through internally generated pseudo-data. We evaluate the proposed method in the Class-Incremental setting, using the split versions of the MNIST and CIFAR10 benchmarks and compare it with FineTune, Experience Replay, Generative Replay, Sleep-Like Replay Consolidation (SRC) and Joint training. Our results show that EB-Gen significantly improves stability while preserving plasticity, achieving a 75\% and 64\% average accuracy on Split MNIST and Split CIFAR10 respectively. These findings show that Equilibrium Propagation can be adapted to alleviate catastrophic forgetting without forgoing the traits which made it compelling in the first place.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{cook2026generative,
  title = {Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks},
  author = {Victor Cook and Gilles Sassatelli and Thierry Gil and Mohamed Watfa and Marina Reyboz},
  year = {2026},
  abstract = {Equilibrium Propagation (EqProp) offers a biologically grounded and hardware-aligned alternative to backpropagation for training Hopfield Networks. However, its behavior in continual learning settings remains largely unexplored. This work confronts catastrophic forgetting in EqProp-trained Hopfield Networks from the inside out, eliminating the need for external data buffers or architectural overhead that standard Experience Replay \textbackslash{}textbf\{(ER)\} and Generative Replay \textbackslash{}textbf\{(Gen-Replay)\} inevita},
  url = {https://arxiv.org/abs/2610.37139},
  keywords = {cs.LG, cs.AI},
  eprint = {2610.37139},
  archiveprefix = {arXiv},
}

Metadata

{}