Scalable Recollections for Continual Lifelong Learning

TL;DR

This paper introduces a scalable architecture and training algorithm for continual lifelong learning that efficiently stores experiences over large time-frames, improving upon existing methods like GEM.

Contribution

The paper proposes a novel scalable memory system and training method for lifelong learning, addressing efficiency in experience storage and retrieval.

Findings

Achieves significant performance improvements over state-of-the-art methods like GEM.

Demonstrates effective experience storage with limited memory resources.

Provides extensive evaluation validating the approach.

Abstract

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong learning system must have three key capabilities: it must learn and adapt over time, it must not forget what it has learned, and it must be efficient in both training time and memory. Recent techniques have focused their efforts primarily on the first two capabilities while questions of efficiency remain largely unexplored. In this paper, we consider the problem of efficient and effective storage of experiences over very large time-frames. In particular we consider the case where typical experiences are O(n) bits and memories are limited to O(k) bits for k << n. We present a novel scalable architecture and training algorithm in this challenging domain and provide an extensive evaluation of its performance. Our results show that we can achieve considerable gains on top of state-of-the-art methods such as GEM.