2026
Rethinking Multi-Instance Learning Through Graph-Driven Fusion: A Dual-Path Approach to Adaptive Representation
AAAI 2026technical
Multi-instance learning (MIL) has become a powerful paradigm for weakly supervised learning tasks, where each sample is a bag of unlabeled instances with only the bag-level label. While graph-based MIL methods enhance bag topological structure modeling, they often suffer from high computation costs