Zzong's Notes

방문

Home

❯

논문

❯

Bias Fairness

❯

Modeling user exposure in recommendation

Modeling user exposure in recommendation

최초 작성 2026-08-28마지막 수정 2026-08-29읽는 데 1분

노트 편집 ↗
  • paper link

링크된 언급

1
Causal Inference for Recommendation

... data). 해당 데이터는 explicit feedback 을 target 으로 한 모델이고, implicit feedback 을 target 으로 한 모델은 Modeling user exposure in recommendation 를 참조 정확히는 이 논문은 vimp 데이터가 명시된 것을 활용한 논문이고, link 가 걸린 paper 는 vimp 데이터가 없어서 inference 를 수행...

함께 보면 좋은 글

Causal Inference for Recommendation

Joint models of exposure and clicks

The Unfairness of Popularity Bias in Recommendation

Calibrated Recommendations

Reference paper: https://dl.acm.org/doi/pdf/10.1145/3240323.3240372 cailbration 의 목적 In the recommended list of items, calibration ensures that the various (past) areas of...

Correcting for Selection Bias in Learning-to-rank Systems

selection bias, which occurs because clicked documents are reflective of what documents have been shown to the user in the first place. propose new counterfactual approaches...

Popularity Bias in Dynamic Recommendation

기존의 모든 popularity bias 연구들은 static 추천 task 를 기반으로 진행했지만, 실제 real-world 에서는 dynamic recommendation 형태를 띈다.

Clicks can be Cheating - Counterfactual Recommendation for Mitigating Clickbait Issue

Related Work Incorporating Various Feedback negative experience identification Between Clicks and Satisfaction - Study on Multi-Phase User Preferences and Satisfaction for...

Recommendations as treatments - debiasing learning and evaluation

추천 시스템에서 학습 또는 평가를 위한 데이터는 대부분 selection bias 에 취약하다.

Combating Selection Biases in Recommender Systems with a Few Unbiased Ratings

Tags selection bias, Abstract Introduction unbiased ratings 포함시키는 방법: 임의로 선택된 일부 아이템들에 대해 유저들에게 rating 을 요청함 Related work Recommendation Debiasing 기존의 debiasing 은 주로 두 가지 측면에...

Debiasing the Human-Recommender System Feedback Loop in Collaborative Filtering

Tags: paper review, matrix factorization , WWW 19

Bias and Debias in Recommender System - A Survey and Future Directions

Blindly fitting the data without considering the inherent biases will result in many serious issues, e.g., the discrepancy between offline evaluation and online metrics,...