Saliency-Guided Hidden Associative Replay for Continual Learning

Published: 27 Oct 2023, Last Modified: 26 Nov 2023AMHN23 PosterEveryoneRevisionsBibTeX
Keywords: Associative Memory, Continual Learning, Memory Replay
TL;DR: In this paper, we propose a general continual learning framework to boost the performance of all replay-based methods by combining the associative memory with continual learning.
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. Amongst various strategies, 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. 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:
Submission Number: 39