Multi-Instance Partial-Label Learning with Margin Adjustment
This work addresses a specific issue in multi-instance partial-label learning, an incremental improvement for researchers in machine learning dealing with weakly supervised data.
The paper tackles the problem of multi-instance partial-label learning, where existing algorithms suffer from suboptimal generalization due to overlooked margins in attention scores and predicted probabilities, and proposes MIPLMA with margin adjustment, which demonstrates superior performance over existing methods in experiments.
Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for attention scores and predicted probabilities, leading to suboptimal generalization performance. A critical issue with these algorithms is that the highest prediction probability of the classifier may appear on a non-candidate label. In this paper, we propose an algorithm named MIPLMA, i.e., Multi-Instance Partial-Label learning with Margin Adjustment, which adjusts the margins for attention scores and predicted probabilities. We introduce a margin-aware attention mechanism to dynamically adjust the margins for attention scores and propose a margin distribution loss to constrain the margins between the predicted probabilities on candidate and non-candidate label sets. Experimental results demonstrate the superior performance of MIPLMA over existing MIPL algorithms, as well as other well-established multi-instance learning algorithms and partial-label learning algorithms.