Causal Learning for Trustworthy Recommender Systems: A Survey

2024-02-13

arXiv.org

AI Summary

Recommendation systems are shifting from relevance modeling toward trustworthy recommendation (TRS), yet existing work predominantly focuses on statistical associations, overlooking the underlying causal nature—thereby limiting fairness, robustness, and explainability. This paper presents the first systematic survey on causal learning for TRS, proposing a “Causality-Driven Trustworthy Recommendation” (CTRS) framework. We introduce the first unified taxonomy covering the entire recommendation pipeline, mapping trust challenges to three core causal methodologies: causal interventions, counterfactual reasoning, and structural causal modeling (SCM). Integrating SCM, do-calculus, causal discovery, and graph-based bias correction, we elucidate how causal mechanisms enhance fairness, robustness, and explainability. Finally, we identify six key future research directions. This work fills a critical gap in the literature by providing the first comprehensive, causality-centered survey of TRS, offering both theoretical foundations and practical guidance for advancing AI-driven trustworthy recommendation paradigms.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

Recommender Systems (RS) have significantly advanced online content filtering and personalized decision-making. However, emerging vulnerabilities in RS have catalyzed a paradigm shift towards Trustworthy RS (TRS). Despite substantial progress on TRS, most efforts focus on data correlations while overlooking the fundamental causal nature of recommendations. This drawback hinders TRS from identifying the root cause of trustworthiness issues, leading to limited fairness, robustness, and explainability. To bridge this gap, causal learning emerges as a class of promising methods to augment TRS. These methods, grounded in reliable causality, excel in mitigating various biases and noise while offering insightful explanations for TRS. However, there is a lack of timely and dedicated surveys in this vibrant area. This paper creates an overview of TRS from the perspective of causal learning. We begin by presenting the advantages and common procedures of Causality-oriented TRS (CTRS). Then, we identify potential trustworthiness challenges at each stage and link them to viable causal solutions, followed by a classification of CTRS methods. Finally, we discuss several future directions for advancing this field.

Problem

• Address vulnerabilities in Recommender Systems
• Enhance fairness, robustness, and explainability
• Incorporate causal learning for Trustworthy RS

Innovation

• Causal learning enhances TRS
• CTRS addresses trustworthiness challenges
• Causality mitigates biases and noise