Curse of "Low" Dimensionality in Recommender Systems
arXiv:2305.13597 · doi:10.1145/3539618.3591659
Abstract
Beyond accuracy, there are a variety of aspects to the quality of recommender systems, such as diversity, fairness, and robustness. We argue that many of the prevalent problems in recommender systems are partly due to low-dimensionality of user and item embeddings, particularly when dot-product models, such as matrix factorization, are used. In this study, we showcase empirical evidence suggesting the necessity of sufficient dimensionality for user/item embeddings to achieve diverse, fair, and robust recommendation. We then present theoretical analyses of the expressive power of dot-product models. Our theoretical results demonstrate that the number of possible rankings expressible under dot-product models is exponentially bounded by the dimension of item factors. We empirically found that the low-dimensionality contributes to a popularity bias, widening the gap between the rank positions of popular and long-tail items; we also give a theoretical justification for this phenomenon.
arXiv commentAccepted by SIGIR'23
References in corpus (10)
- MLlib: Machine Learning in Apache Spark
- Fairness of Exposure in Rankings
- Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
- LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
- Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)
- FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms
- Bias and Debias in Recommender System: A Survey and Future Directions
- Achieving Fairness in the Stochastic Multi-armed Bandit Problem
- ALX: Large Scale Matrix Factorization on TPUs
- Fair Matrix Factorisation for Large-Scale Recommender Systems