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

TL;DR

This paper introduces the Causal Cooperative Game framework for multi-label classification, combining causal discovery, counterfactual reasoning, and cooperative game theory to improve robustness and rare label prediction.

Contribution

It presents a novel framework that integrates causal inference with cooperative game theory, enhancing multi-label classification under challenging conditions.

Findings

Significantly outperforms baselines in rare label prediction

Demonstrates robustness across diverse environments

Provides interpretability through ablation and qualitative analysis

Abstract

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.