Controlling Popularity Bias in Learning-to-Rank Recommendation

By Himan Abdollahpouri, Robin D. Burke, Bamshad Mobasher. ACM Conference on Recommender Systems, 2017

447 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/8b8f4e39b6a30462b2c411f971ec2316fa8d7da2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Fuli Feng
4. Yong Li
5. Chen Gao
6. Meng Wang
7. Tat-seng Chua
8. Yongfeng Zhang

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Fuli Feng
4. Yongfeng Zhang
5. Meng Wang
6. Yong Li
7. Chen Gao
8. Dietmar Jannach

In Management Science and Operations Research

1. Xiangnan He
2. Fuli Feng
3. Xiang Wang
4. Meng Wang
5. Robin D. Burke
6. Tianxin Wei
7. Himan Abdollahpouri
8. Dietmar Jannach

Citations in the corpus

• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, background): “Here, we focus on the user fairness, and leave item fairness in the section of diversity for their close connection in terms of interpretations and solutions [2, 125].”
• Causal Intervention for Leveraging Popularity Bias in Recommendation (2021, methodology): “On one hand, the user-item interaction data usually exhibits long-tail distribution on item popularity — a few head items occupy most of the interactions whereas the majority of items receive relatively little attention [2, 30].”
• Multistakeholder recommendation: Survey and research directions (2020, background): “e is a large body of recent work on incorporating diversity, novelty, long tail promotion and other metrics as 10 additional objectives for recommendation generation and evaluation. See, for example, [1, 126, 146, 133, 69]. There is also a growing body of work on combining multiple objectives using ”
• Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System (2020, methodology): “• As to baselines for popularity debias, Reg method [2] have limited improvement over the basic models and even sometimes perform even worse.”
• User-oriented Fairness in Recommendation (2021, background): “Such researches mainly solve this problem by increasing the number of recommended unpopular items (long-tail items) or otherwise the overall catalog coverage [2, 3, 5, 21].”
• Disentangling User Interest and Conformity for Recommendation with Causal Embedding (2021, background): “Existing causal solutions for recommender systems formulate the problem as eliminating popularity bias, from the perspective of items [1, 3, 5, 11, 12, 24, 35, 43].”
• Managing Popularity Bias in Recommender Systems with Personalized Re-ranking (2019, methodology): “A regularization-based approach to improving long tail recommendations is found in (Abdollahpouri, Burke, and Mobasher 2017a).”
• Bias and Debias in Recommender System: A Survey and Future Directions (2020, methodology): “Popularity Bias Regularization [106], [107], [108], [109] Adversarial learning [110] Causal graph [32] Others [111], [112]”