Affiliation:
1. National University of Singapore, Singapore
2. University of Science and Technology of China, China
Abstract
In leading collaborative filtering (CF) models, representations of users and items are prone to learn popularity bias in the training data as shortcuts. The popularity shortcut tricks are good for in-distribution (ID) performance but poorly generalized to out-of-distribution (OOD) data, i.e., when popularity distribution of test data shifts w.r.t. the training one. To close the gap, debiasing strategies try to assess the shortcut degrees and mitigate them from the representations. However, there exist two deficiencies: (1) when measuring the shortcut degrees, most strategies only use statistical metrics on a single aspect (i.e., item frequency on item and user frequency on user aspect), failing to accommodate the compositional degree of a user–item pair; (2) when mitigating shortcuts, many strategies assume that the test distribution is known in advance. This results in low-quality debiased representations. Worse still, these strategies achieve OOD generalizability with a sacrifice on ID performance.
In this work, we present a simple yet effective debiasing strategy,
PopGo
, which quantifies and reduces the interaction-wise popularity shortcut without any assumptions on the test data. It first learns a shortcut model, which yields a shortcut degree of a user–item pair based on their popularity representations. Then, it trains the CF model by adjusting the predictions with the interaction-wise shortcut degrees. By taking both causal- and information-theoretical looks at PopGo, we can justify why it encourages the CF model to capture the critical popularity-agnostic features while leaving the spurious popularity-relevant patterns out. We use PopGo to debias two high-performing CF models (matrix factorization [
28
] and LightGCN [
19
]) on four benchmark datasets. On both ID and OOD test sets, PopGo achieves significant gains over the state-of-the-art debiasing strategies (e.g., DICE [
71
] and MACR [
58
]). Codes and datasets are available at
https://github.com/anzhang314/PopGo
.
Funder
National Natural Science Foundation of China
University Synergy Innovation Program of Anhui Province
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Science Applications,General Business, Management and Accounting,Information Systems
Reference74 articles.
1. Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2017. Controlling popularity bias in learning-to-rank recommendation. In RecSys. 42–46.
2. Himan Abdollahpouri, Masoud Mansoury, Robin Burke, and Bamshad Mobasher. 2019. The unfairness of popularity bias in recommendation. In RMSE@RecSys (CEUR Workshop Proceedings), Vol. 2440.
3. The Bellkor 2008 Solution to the Netflix Prize;Bell Robert M.;Statistics Research Department at AT & T Research,2008
4. Statistical biases in Information Retrieval metrics for recommender systems
5. Stephen Bonner and Flavian Vasile. 2018. Causal embeddings for recommendation. In RecSys. 104–112.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献