Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts

• Main Authors: Liu, Yuejiang, Alahi, Alexandre
• Format: Journal Article
• Language: English
• Published: 23.02.2024
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
• DOI: 10.48550/arxiv.2402.15505

Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors. Recent studies reveal that, despite supervisory noises, a strong student model may surpass its weak teacher when fine-tuned on specific objectives. Yet, the effectiveness of such weak-to-strong generalization remains limited, especially in the presence of large capability gaps. In this paper, we propose to address this challenge by harnessing a diverse set of specialized teachers, instead of a single generalist one, that collectively supervises the strong student. Our approach resembles the classical hierarchical mixture of experts, with two components tailored for co-supervision: (i) we progressively alternate student training and teacher assignment, leveraging the growth of the strong student to identify plausible supervisions; (ii) we conservatively enforce teacher-student and local-global consistency, leveraging their dependencies to reject potential annotation noises. We validate the proposed method through visual recognition tasks on the OpenAI weak-to-strong benchmark and additional multi-domain datasets. Our code is available at \url{https://github.com/yuejiangliu/csl}.