LGJun 6, 2024

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples

arXiv:2406.03944v15 citations
Originality Incremental advance
AI Analysis

This work offers theoretical insights for researchers in active learning, but it is incremental as it builds on existing criteria without introducing a new method.

The paper tackled the lack of understanding of uncertainty-based and diversity-based neural active learning by providing a unified explanation from a feature learning view, proving that both criteria succeed by prioritizing samples with yet-to-be-learned features, which reduces test error with a small labeled set compared to passive learning.

Neural Network-based active learning (NAL) is a cost-effective data selection technique that utilizes neural networks to select and train on a small subset of samples. While existing work successfully develops various effective or theory-justified NAL algorithms, the understanding of the two commonly used query criteria of NAL: uncertainty-based and diversity-based, remains in its infancy. In this work, we try to move one step forward by offering a unified explanation for the success of both query criteria-based NAL from a feature learning view. Specifically, we consider a feature-noise data model comprising easy-to-learn or hard-to-learn features disrupted by noise, and conduct analysis over 2-layer NN-based NALs in the pool-based scenario. We provably show that both uncertainty-based and diversity-based NAL are inherently amenable to one and the same principle, i.e., striving to prioritize samples that contain yet-to-be-learned features. We further prove that this shared principle is the key to their success-achieve small test error within a small labeled set. Contrastingly, the strategy-free passive learning exhibits a large test error due to the inadequate learning of yet-to-be-learned features, necessitating resort to a significantly larger label complexity for a sufficient test error reduction. Experimental results validate our findings.

Foundations

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

Your Notes