Neural Weight Search for Scalable Task Incremental Learning
This addresses the memory growth issue in task incremental learning for AI systems that need to learn multiple tasks sequentially.
The paper tackles the problem of catastrophic forgetting in task incremental learning by introducing Neural Weight Search, which searches for optimal combinations of frozen weights to build new models for novel tasks, achieving state-of-the-art performance on benchmarks like Split-CIFAR-100 and CUB-to-Sketches with improved accuracy and memory efficiency.
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.