Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fan, Yijia, Zhang, Jusheng, Cai, Kaitong, Yang, Jing, Wang, Keze
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917114508476416
author Fan, Yijia
Zhang, Jusheng
Cai, Kaitong
Yang, Jing
Wang, Keze
author_facet Fan, Yijia
Zhang, Jusheng
Cai, Kaitong
Yang, Jing
Wang, Keze
contents Multi-label classification (MLC) remains vulnerable to label imbalance, spurious correlations, and distribution shifts, challenges that are particularly detrimental to rare label prediction. To address these limitations, we introduce the Causal Cooperative Game (CCG) framework, which conceptualizes MLC as a cooperative multi-player interaction. CCG unifies explicit causal discovery via Neural Structural Equation Models with a counterfactual curiosity reward to drive robust feature learning. Furthermore, it incorporates a causal invariance loss to ensure generalization across diverse environments, complemented by a specialized enhancement strategy for rare labels. Extensive benchmarking demonstrates that CCG substantially outperforms strong baselines in both rare label prediction and overall robustness. Through rigorous ablation studies and qualitative analysis, we validate the efficacy and interpretability of our components, underscoring the potential of synergizing causal inference with cooperative game theory for advancing multi-label learning.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00812
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification
Fan, Yijia
Zhang, Jusheng
Cai, Kaitong
Yang, Jing
Wang, Keze
Machine Learning
Artificial Intelligence
Multi-label classification (MLC) remains vulnerable to label imbalance, spurious correlations, and distribution shifts, challenges that are particularly detrimental to rare label prediction. To address these limitations, we introduce the Causal Cooperative Game (CCG) framework, which conceptualizes MLC as a cooperative multi-player interaction. CCG unifies explicit causal discovery via Neural Structural Equation Models with a counterfactual curiosity reward to drive robust feature learning. Furthermore, it incorporates a causal invariance loss to ensure generalization across diverse environments, complemented by a specialized enhancement strategy for rare labels. Extensive benchmarking demonstrates that CCG substantially outperforms strong baselines in both rare label prediction and overall robustness. Through rigorous ablation studies and qualitative analysis, we validate the efficacy and interpretability of our components, underscoring the potential of synergizing causal inference with cooperative game theory for advancing multi-label learning.
title Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.00812