Saliency-Guided Hidden Associative Replay for Continual Learning
Primary Area: transfer learning, meta learning, and lifelong learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Continual Learning, Memory Replay, Associative Memory
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: This paper proposed a novel neuro-inspired continual learning framework based on associative memory and experience replay.
Abstract: Continual Learning (CL) is a burgeoning domain in next-generation AI, focusing on training neural networks over a sequence of tasks akin to human learning. While CL provides an edge over traditional supervised learning, its central challenge remains to counteract \emph{catastrophic forgetting} and ensure the retention of prior tasks during subsequent learning. Amongst various strategies to tackle this, replay-based methods have emerged as preeminent, echoing biological memory mechanisms. However, these methods are memory-intensive, often preserving entire data samples—an approach inconsistent with humans' selective memory retention of salient experiences. While some recent works have explored the storage of only significant portions of data in episodic memory, the inherent nature of partial data necessitates innovative retrieval mechanisms. Current solutions, like inpainting, approximate full data reconstruction from partial cues, a method that diverges from genuine human memory processes. Addressing these nuances, this paper presents the **S**aliency-Guided **H**idden **A**ssociative **R**eplay for **C**ontinual Learning (**SHARC**). This novel framework synergizes associative memory with replay-based strategies. SHARC primarily archives salient data segments via sparse memory encoding. Importantly, by harnessing associative memory paradigms, it introduces a content-focused memory retrieval mechanism, promising swift and near-perfect recall, bringing CL a step closer to authentic human memory processes. Extensive experimental results demonstrate the effectiveness of our proposed method for various continual learning tasks. Anonymous code can be found at: https://anonymous.4open.science/r/SHARC-6319.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6396
Loading