Unbiased Recommender Systems with Implicit Feedback
2026-08-17 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors study how recommender systems, like those suggesting movies or products, can be biased because of where items appear on a list (position bias) and how often popular items are shown (popularity bias). They focus on fixing these biases in two types of recommendation methods: learning-to-rank systems and collaborative filtering models that use social network information. Their new methods help the systems better understand what users truly like rather than just what is clicked more due to positioning or popularity. This aims to make recommendations more accurate and personalized.
recommender systemsimplicit feedbackposition biaspopularity biaslearning-to-rank (LTR)collaborative filtering (CF)graph neural networksuser preferencespersonalizationbias mitigation
Authors
Md Aminul Islam
Abstract
Recommender systems typically rely on implicit feedback (e.g., clicks) to infer user preferences. However, such data is inherently prone to various biases, including position bias and popularity bias. Position bias occurs when higher-ranked items receive more interactions regardless of true relevance. Popularity bias reinforces frequent exposure of popular items while under-recommending relevant, yet less popular ones. Directly learning from such data fails to capture true user preferences, leading to suboptimal recommendations. This research focuses on mitigating position bias and popularity bias in recommender systems. Specifically, I address position bias in learning-to-rank (LTR) systems and popularity bias in collaborative filtering (CF) models and social recommender systems based on graph neural networks. My work develops methods that overcome the limitations of existing approaches to mitigating position bias and popularity bias, enabling more relevant and personalized recommendations that align with users' preferences.