Task-Core Memory Management and Consolidation for Long-term Continual Learning

TL;DR

This paper introduces a novel long-term continual learning framework inspired by human memory, featuring task-core memory management and consolidation mechanisms to mitigate catastrophic forgetting over extensive task streams.

Contribution

It proposes a new memory management and consolidation framework for long-term CL, along with two benchmarks for evaluating such methods.

Findings

Long-CL outperforms previous methods by 7.4% and 6.5% AP on new benchmarks.

The proposed approach effectively reduces catastrophic forgetting in long-term CL.

Benchmarks facilitate future research in long-term continual learning.

Abstract

In this paper, we focus on a long-term continual learning (CL) task, where a model learns sequentially from a stream of vast tasks over time, acquiring new knowledge while retaining previously learned information in a manner akin to human learning. Unlike traditional CL settings, long-term CL involves handling a significantly larger number of tasks, which exacerbates the issue of catastrophic forgetting. Our work seeks to address two critical questions: 1) How do existing CL methods perform in the context of long-term CL? and 2) How can we mitigate the catastrophic forgetting that arises from prolonged sequential updates? To tackle these challenges, we propose a novel framework inspired by human memory mechanisms for long-term continual learning (Long-CL). Specifically, we introduce a task-core memory management strategy to efficiently index crucial memories and adaptively update them as learning progresses. Additionally, we develop a long-term memory consolidation mechanism that selectively retains hard and discriminative samples, ensuring robust knowledge retention. To facilitate research in this area, we construct and release two multi-modal and textual benchmarks, MMLongCL-Bench and TextLongCL-Bench, providing a valuable resource for evaluating long-term CL approaches. Experimental results show that Long-CL outperforms the previous state-of-the-art by 7.4\% and 6.5\% AP on the two benchmarks, respectively, demonstrating the effectiveness of our approach.