VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference

TL;DR

This paper introduces VERSE, a streaming lifelong learning method that uses virtual gradients and semantic memory to learn continuously in dynamic environments without forgetting, enabling real-time inference.

Contribution

The paper presents a novel virtual-gradient approach combined with semantic memory for effective class-incremental streaming lifelong learning.

Findings

Outperforms existing lifelong learning methods on diverse datasets.

Effectively prevents catastrophic forgetting in non-stationary environments.

Supports anytime inference with single-pass data processing.

Abstract

Lifelong learning or continual learning is the problem of training an AI agent continuously while also preventing it from forgetting its previously acquired knowledge. Streaming lifelong learning is a challenging setting of lifelong learning with the goal of continuous learning in a dynamic non-stationary environment without forgetting. We introduce a novel approach to lifelong learning, which is streaming (observes each training example only once), requires a single pass over the data, can learn in a class-incremental manner, and can be evaluated on-the-fly (anytime inference). To accomplish these, we propose a novel \emph{virtual gradients} based approach for continual representation learning which adapts to each new example while also generalizing well on past data to prevent catastrophic forgetting. Our approach also leverages an exponential-moving-average-based semantic memory to further enhance performance. Experiments on diverse datasets with temporally correlated observations demonstrate our method's efficacy and superior performance over existing methods.