Deconfounded Recommendation for Alleviating Bias Amplification

Abstract

Recommender systems usually amplify the biases in the data. The model learned from historical interactions with imbalanced item distribution will amplify the imbalance by over-recommending items from the major groups. Addressing this issue is essential for a healthy ecosystem of recommendation in the long run. Existing works apply bias control to the ranking targets (e.g., calibration, fairness, and diversity), but ignore the true reason for bias amplification and trade-off the recommendation accuracy. In this work, we scrutinize the cause-effect factors for bias amplification, identifying the main reason lies in the confounder effect of imbalanced item distribution on user representation and prediction score. The existence of such confounder pushes us to go beyond merely modeling the conditional probability and embrace the causal modeling for recommendation. Towards this end, we propose a Deconfounded Recommender System (DecRS), which models the causal effect of user representation on the prediction score. The key to eliminating the impact of the confounder lies in backdoor adjustment, which is however difficult to do due to the infinite sample space of the confounder. For this challenge, we contribute an approximation operator for backdoor adjustment which can be easily plugged into most recommender models. Lastly, we devise an inference strategy to dynamically regulate backdoor adjustment according to user status. We instantiate DecRS on two representative models FM and NFM, and conduct extensive experiments over two benchmarks to validate the superiority of our proposed DecRS.

References in corpus (11)

• Neural Graph Collaborative Filtering
• Disentangled Graph Collaborative Filtering
• Fairness of Exposure in Rankings
• Causal Intervention for Leveraging Popularity Bias in Recommendation
• How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility
• Equity of Attention: Amortizing Individual Fairness in Rankings
• Denoising Implicit Feedback for Recommendation
• Causal Embeddings for Recommendation
• Controlling Fairness and Bias in Dynamic Learning-to-Rank
• Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue
• Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method

Cited by in corpus (19)

• Representation Learning with Large Language Models for Recommendation
• Disentangled Contrastive Collaborative Filtering
• User-controllable Recommendation Against Filter Bubbles
• Invariant Collaborative Filtering to Popularity Distribution Shift
• Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations
• Deconfounded Causal Collaborative Filtering
• Causal Collaborative Filtering
• How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective
• Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
• Contextual Distillation Model for Diversified Recommendation
• LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
• The Importance of Causality in Decision Making: A Perspective on Recommender Systems
• Ada-Ranker: A Data Distribution Adaptive Ranking Paradigm for Sequential Recommendation
• Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
• Causality-Inspired Fair Representation Learning for Multimodal Recommendation
• Decoy Effect In Search Interaction: Understanding User Behavior and Measuring System Vulnerability
• Automatic Feature Fairness in Recommendation via Adversaries
• Unconstrained Monotonic Calibration of Predictions in Deep Ranking Systems
• Not All Videos Become Outdated: Short-Video Recommendation by Learning to Deconfound Release Interval Bias