Explainable Distributed Constraint Optimization Problems

2025-02-19

AI Summary

Distributed Constraint Optimization Problems (DCOPs) suffer from poor solution interpretability, hindering real-world deployment. Method: This paper introduces Explainable DCOP (X-DCOP), the first DCOP framework natively integrating interpretability. It jointly models optimal solutions and contrastive explanations, formally defining conditions for explanation validity. A distributed solving framework is developed, along with multiple optimization variants that trade off explanation conciseness against computational overhead. Contribution/Results: Theoretically, X-DCOP establishes foundational guarantees for explanation validity. Empirically, it scales to large-scale DCOP instances. Human-subject experiments confirm users prefer concise explanations and demonstrate that the variants enable flexible, on-demand balancing of explanation quality and computational efficiency.

Technology Category

• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Distributed Search
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The Distributed Constraint Optimization Problem (DCOP) formulation is a powerful tool to model cooperative multi-agent problems that need to be solved distributively. A core assumption of existing approaches is that DCOP solutions can be easily understood, accepted, and adopted, which may not hold, as evidenced by the large body of literature on Explainable AI. In this paper, we propose the Explainable DCOP (X-DCOP) model, which extends a DCOP to include its solution and a contrastive query for that solution. We formally define some key properties that contrastive explanations must satisfy for them to be considered as valid solutions to X-DCOPs as well as theoretical results on the existence of such valid explanations. To solve X-DCOPs, we propose a distributed framework as well as several optimizations and suboptimal variants to find valid explanations. We also include a human user study that showed that users, not surprisingly, prefer shorter explanations over longer ones. Our empirical evaluations showed that our approach can scale to large problems, and the different variants provide different options for trading off explanation lengths for smaller runtimes. Thus, our model and algorithmic contributions extend the state of the art by reducing the barrier for users to understand DCOP solutions, facilitating their adoption in more real-world applications.

Problem

• Extends DCOP for explainable solutions
• Defines properties for valid contrastive explanations
• Proposes scalable distributed framework for X-DCOPs

Innovation

• Explainable DCOP model
• Contrastive query solutions
• Distributed framework optimizations