Neural Weight Search for Scalable Task Incremental Learning

TL;DR

This paper introduces a Neural Weight Search method for task incremental learning that efficiently builds new task models by searching for optimal weight combinations within a fixed space, reducing memory growth.

Contribution

It proposes a scalable, end-to-end neural weight search technique that maintains performance while controlling memory expansion in task incremental learning.

Findings

Achieves state-of-the-art accuracy on Split-CIFAR-100 and CUB-to-Sketches benchmarks.

Reduces total memory cost compared to existing methods.

Maintains performance with a fixed search space for weight combinations.

Abstract

Task incremental learning aims to enable a system to maintain its performance on previously learned tasks while learning new tasks, solving the problem of catastrophic forgetting. One promising approach is to build an individual network or sub-network for future tasks. However, this leads to an ever-growing memory due to saving extra weights for new tasks and how to address this issue has remained an open problem in task incremental learning. In this paper, we introduce a novel Neural Weight Search technique that designs a fixed search space where the optimal combinations of frozen weights can be searched to build new models for novel tasks in an end-to-end manner, resulting in scalable and controllable memory growth. Extensive experiments on two benchmarks, i.e., Split-CIFAR-100 and CUB-to-Sketches, show our method achieves state-of-the-art performance with respect to both average inference accuracy and total memory cost.