Heuristic-Free Multi-Teacher Learning
This addresses the issue of aggregation errors in multi-teacher learning for machine learning practitioners, representing a novel method rather than an incremental improvement.
The paper tackles the problem of sub-optimal aggregated labels and error propagation in multi-teacher learning by introducing Teacher2Task, a framework that eliminates manual aggregation heuristics and reformulates training into multiple tasks, achieving strong empirical results across various architectures, modalities, and tasks.
We introduce Teacher2Task, a novel framework for multi-teacher learning that eliminates the need for manual aggregation heuristics. Existing multi-teacher methods typically rely on such heuristics to combine predictions from multiple teachers, often resulting in sub-optimal aggregated labels and the propagation of aggregation errors. Teacher2Task addresses these limitations by introducing teacher-specific input tokens and reformulating the training process. Instead of relying on aggregated labels, the framework transforms the training data, consisting of ground truth labels and annotations from N teachers, into N+1 distinct tasks: N auxiliary tasks that predict the labeling styles of the N individual teachers, and one primary task that focuses on the ground truth labels. This approach, drawing upon principles from multiple learning paradigms, demonstrates strong empirical results across a range of architectures, modalities, and tasks.