Multi-Instance Partial-Label Learning with Margin Adjustment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915115475927040 |
|---|---|
| author | Tang, Wei Yang, Yin-Fang Wang, Zhaofei Zhang, Weijia Zhang, Min-Ling |
| author_facet | Tang, Wei Yang, Yin-Fang Wang, Zhaofei Zhang, Weijia Zhang, Min-Ling |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12597 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Instance Partial-Label Learning with Margin Adjustment Tang, Wei Yang, Yin-Fang Wang, Zhaofei Zhang, Weijia Zhang, Min-Ling Machine Learning 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. |
| title | Multi-Instance Partial-Label Learning with Margin Adjustment |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.12597 |