Dynamic Causal Collaborative Filtering

Abstract

Causal graph, as an effective and powerful tool for causal modeling, is usually assumed as a Directed Acyclic Graph (DAG). However, recommender systems usually involve feedback loops, defined as the cyclic process of recommending items, incorporating user feedback in model updates, and repeating the procedure. As a result, it is important to incorporate loops into the causal graphs to accurately model the dynamic and iterative data generation process for recommender systems. However, feedback loops are not always beneficial since over time they may encourage more and more narrowed content exposure, which if left unattended, may results in echo chambers. As a result, it is important to understand when the recommendations will lead to echo chambers and how to mitigate echo chambers without hurting the recommendation performance. In this paper, we design a causal graph with loops to describe the dynamic process of recommendation. We then take Markov process to analyze the mathematical properties of echo chamber such as the conditions that lead to echo chambers. Inspired by the theoretical analysis, we propose a Dynamic Causal Collaborative Filtering ($\partial$CCF) model, which estimates users' post-intervention preference on items based on back-door adjustment and mitigates echo chamber with counterfactual reasoning. Multiple experiments are conducted on real-world datasets and results show that our framework can mitigate echo chambers better than other state-of-the-art frameworks while achieving comparable recommendation performance with the base recommendation models.

arXiv commentIn ACM CIKM 2022

References in corpus (17)

• Explainable Recommendation: A Survey and New Perspectives
• How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility
• Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
• Causal Embeddings for Recommendation
• Degenerate Feedback Loops in Recommender Systems
• Personalized Counterfactual Fairness in Recommendation
• Opinion Polarization by Learning from Social Feedback
• Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
• Neural Collaborative Reasoning
• Political Discourse on Social Media: Echo Chambers, Gatekeepers, and the Price of Bipartisanship
• Explainable Fairness in Recommendation
• Unbiased Learning for the Causal Effect of Recommendation
• Conformity, anticonformity and polarization of opinions: insights from a mathematical model of opinion dynamics
• Causal Collaborative Filtering
• A Survey on Trustworthy Recommender Systems
• Fairness in Recommendation: Foundations, Methods and Applications
• Tell me something my friends do not know: Diversity maximization in social networks

Cited by in corpus (4)

• Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation
• Deconfounded Causal Collaborative Filtering
• Large Language Models are Learnable Planners for Long-Term Recommendation
• Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS)