Zzong's Notes

Home

❯

papers

❯

evaluation

❯

Evaluating Stochastic Rankings with Expected Exposure

Evaluating Stochastic Rankings with Expected Exposure

2026년 8월 29일1 min read

  • Links
    • paper: https://arxiv.org/pdf/2004.13157.pdf

링크된 언급

1
Top-K Contextual Bandits with Equity of Exposure

Evaluating Stochastic Rankings with Expected Exposure: equity of exposure principle 제안, exploiting the stochasticity of rankings to lead...

함께 보면 좋은 글

Top-K Contextual Bandits with Equity of Exposure

Abstract Probability Ranking Principle 에 의하면 top-K items 을 greedy 하게 rank 하는것이 optimal 함 대신 Introduction This work investigates how the “equity of exposure” principle can be...

Unbiased Learning-to-Rank with Biased Feedback

Abstract implicit feedback 을 Learning-to-Rank 방식에 학습할 때 발생하는 bias (e.g., position bias) 를 줄이기 위해 counterfactual inference framework 를 제안 In contrast to most conventional...

Offline AB testing for Recommender Systems

Notation 현재 production policy \pi p 그리고 test policy \pi t X: contextual feature 에 대한 random variable \pi(A\mid X) 는 action A 에 대한 확률 분포 Offline A/B Test 테스트를 수행하기 위해서는...

Towards Unified Metrics for Accuracy and Diversity for Recommender Systems

Abstract offline evaluation 평가에서 중요한건 accuracy 인데, diversity 도 중요하다. 그래서 이 논문에서는 둘을 통합한 metric 을 만들었다. 그리고 제안한 metric 이 일부 속성들을 만족함을 보였다.

Correcting for Selection Bias in Learning-to-rank Systems

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

Unbiased Offline Recommender Evaluation for Missing-Not-At-Random Implicit Feedback

Paper link Abstract (a) investigate evaluation bias of AOA(Average-Over-All) evaluator (b) an unbiased and practical offline evaluator for implicit MNAR datasets 를 제안 the...

추천시스템에서 Unbiased Offline Evaluation

핵심 요약 추천 시스템을 온라인 A/B 테스트 없이 오프라인에서 평가하는 방법론. Logging policy로 수집된 편향된 데이터에서 새로운 policy의 성능을 unbiased하게 추정하는 것이 핵심 과제다.

Online learning to rank for information retrieval

References slide: staff.fnwi.uva.nl/m.derijke/wp-content/uploads/sigir2016-tutorial.pdf .

Calibrated Recommendations

Reference paper: 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 interest of...

The Unfairness of Popularity Bias in Recommendation

paper link.