---
title: "Label Confidence Recovery with High-order Label Correlation in Partial Multi-label Learning"
authors:
  - "Yuanchao Dai"
  - "Ximing Li"
  - "Ming-Kun Xie"
  - "Xurui Li"
  - "Changchun Li"
doi: "10.24963/ijcai.2026/472"
url: "https://ijcai.org/proceedings/2026/472"
pdf: "https://ijcai.org/proceedings/2026/0472.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "4242-4250"
track: "Main Track"
keywords:
  - "Machine Learning: Weakly supervised learning"
---

# Label Confidence Recovery with High-order Label Correlation in Partial Multi-label Learning

Yuanchao Dai, Ximing Li, Ming-Kun Xie, Xurui Li, Changchun Li

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 4242-4250. DOI: [10.24963/ijcai.2026/472](https://doi.org/10.24963/ijcai.2026/472)

## Abstract

Partial multi-label learning (PML) addresses weakly-supervised scenarios where each instance is associated with a candidate label set containing both ground-truth and noisy labels. Existing PML methods primarily focus on instance-level features or pairwise label correlations for disambiguation. Building on recent insights that exploiting pairwise label correlations improves disambiguation, we observe that high-order label correlations provide even stronger disambiguation evidence in partial settings because ground-truth labels with high-order correlations frequently co-occur, while noise labels produce inconsistent combinations that rarely repeat. To exploit this property, we propose REHC-PML (Label Confidence REcovery with High-order Label Correlations in Partial Multi-label Learning), which mines frequent high-order co-occurrences from candidate sets to identify global high-order label correlations, selects instance-relevant correlations via Gumbel-Softmax pruning, and propagates their evidence to constituent labels for confidence recovery. Self-training iteratively refines pseudo-labels and trains the classifier. Extensive experiments on both real-world and UCI datasets demonstrate the effectiveness of REHC-PML.