GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

2024-05-29

arXiv.org

AI Summary

This paper addresses the problem of global counterfactual explanation for high-stakes decision-making, proposing a tri-objective co-optimization framework that simultaneously ensures explanation effectiveness (i.e., high population coverage), minimizes individual intervention cost, and strictly constrains the total number of actionable features to enhance interpretability. To this end, we introduce two novel algorithms: C-GLANCE, which jointly clusters feature and action spaces, and T-GLANCE, which learns customizable, tree-structured subgroup policies. These are the first methods to jointly model effectiveness, low intervention cost, and action sparsity. Our approach integrates clustering analysis, counterfactual generation, decision tree modeling, and subgroup policy learning. Extensive experiments across multiple datasets and black-box models demonstrate significant improvements over state-of-the-art baselines: up to 18.7% higher coverage, up to 23.4% lower average intervention cost, and superior robustness.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Causal Learning
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The widespread deployment of machine learning systems in critical real-world decision-making applications has highlighted the urgent need for counterfactual explainability methods that operate effectively. Global counterfactual explanations, expressed as actions to offer recourse, aim to provide succinct explanations and insights applicable to large population subgroups. Effectiveness is measured by the fraction of the population that is provided recourse, ensuring that the actions benefit as many individuals as possible. Keeping the cost of actions low ensures the proposed recourse actions remain practical and actionable. Limiting the number of actions that provide global counterfactuals is essential to maximize interpretability. The primary challenge, therefore, is balancing these trade-offs, i.e., maximizing effectiveness, minimizing cost, while maintaining a small number of actions. We introduce GLANCE, a versatile and adaptive framework, comprising two algorithms, that allows the careful balancing of the trade-offs among the three key objectives, with the size objective functioning as a tunable parameter to keep the actions few and easy to interpret. C-GLANCE employs a clustering approach that considers both the feature space and the space of counterfactual actions, thereby accounting for the distribution of points in a way that aligns with the structure of the model. T-GLANCE provides additional features to enhance flexibility. It employs a tree-based approach, that allows users to specify split features, to build a decision tree with a single counterfactual action at each node that can be used as a subgroup policy. Our extensive experimental evaluation demonstrates that our method consistently shows greater robustness and performance compared to existing methods across various datasets and models.

Problem

• Balancing effectiveness, cost, and action count in counterfactual explanations
• Providing global recourse actions for large population subgroups
• Ensuring explanations are practical, actionable, and interpretable

Innovation

• Agglomerative approach for counterfactual explainability
• Balances effectiveness, cost, and action count
• Jointly considers feature and counterfactual action spaces