LGCVApr 19, 2024

Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation

arXiv:2404.12766v28 citationsh-index: 21ICLR
Originality Incremental advance
AI Analysis

This addresses a realistic challenge for continual learning systems where computational resources and labeled data are scarce, though it is incremental as it builds on existing semi-supervised and continual learning approaches.

The paper tackles the problem of continual learning with limited computational budgets and sparse labeled data, proposing DietCL, which outperforms existing methods by large margins on datasets like CLOC, ImageNet10K, and CGLM.

We propose and study a realistic Continual Learning (CL) setting where learning algorithms are granted a restricted computational budget per time step while training. We apply this setting to large-scale semi-supervised Continual Learning scenarios with sparse label rates. Previous proficient CL methods perform very poorly in this challenging setting. Overfitting to the sparse labeled data and insufficient computational budget are the two main culprits for such a poor performance. Our new setting encourages learning methods to effectively and efficiently utilize the unlabeled data during training. To that end, we propose a simple but highly effective baseline, DietCL, which utilizes both unlabeled and labeled data jointly. DietCL meticulously allocates computational budget for both types of data. We validate our baseline, at scale, on several datasets, e.g., CLOC, ImageNet10K, and CGLM, under constraint budget setups. DietCL outperforms, by a large margin, all existing supervised CL algorithms as well as more recent continual semi-supervised methods. Our extensive analysis and ablations demonstrate that DietCL is stable under a full spectrum of label sparsity, computational budget, and various other ablations.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes