paper-with-me

Papers

Recommendation or Discrimination?: Quantifying Distribution Parity in Information Retrieval Systems

2019-09-13 · Rinat Khaziev, Bryce Casavant, Pearce Washabaugh, Amy A. Winecoff, Matthew Graham

Information retrieval (IR) systems often leverage query data to suggest relevant items to users. This introduces the possibility of unfairness if the query (i.e., input) and the resulting recommendations unintentionally correlate with latent factors that are protected variables (e.g., race, gender, and age). For instance, a visual search system for fashion recommendations may pick up on features of the human models rather than fashion garments when generating recommendations. In this work, we introduce a statistical test for "distribution parity" in the top-K IR results, which assesses whether a given set of recommendations is fair with respect to a specific protected variable. We evaluate our test using both simulated and empirical results. First, using artificially biased recommendations, we demonstrate the trade-off between statistically detectable bias and the size of the search catalog. Second, we apply our test to a visual search system for fashion garments, specifically testing for recommendation bias based on the skin tone of fashion models. Our distribution parity test can help ensure that IR systems' results are fair and produce a good experience for all users.

📄 PDF Abstract BibTeX arXiv:1909.06429

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalRetrieval

Similar Papers 제목 키워드 기반

Exploring Artist Gender Bias in Music Recommendation

2020-09-03 · Dougal Shakespeare, Lorenzo Porcaro, Emilia Gómez, Carlos Castillo

Music Recommender Systems (mRS) are designed to give personalised and meaningful recommendations of items (i.e. songs, playlists or artists) to a user base, thereby reflecting and further complementing individual users' …

Collaborative FilteringMusic RecommendationRecommendation Systems

User Fairness in Recommender Systems

2018-07-17 · Leonhardt Jurek, Anand Avishek, Khosla Megha

Recent works in recommendation systems have focused on diversity in recommendations as an important aspect of recommendation quality. In this work we argue that the post-processing algorithms aimed at only improving dive…

DiversityFairnessRecommendation Systems

On conditional parity as a notion of non-discrimination in machine learning

2017-06-26 · Ya'acov Ritov, Yuekai Sun, Ruofei Zhao

We identify conditional parity as a general notion of non-discrimination in machine learning. In fact, several recently proposed notions of non-discrimination, including a few counterfactual notions, are instances of con…

BIG-bench Machine Learningcounterfactual

Quantifying Feature Contributions to Overall Disparity Using Information Theory

2022-06-16 · Sanghamitra Dutta, Praveen Venkatesh, Pulkit Grover

When a machine-learning algorithm makes biased decisions, it can be helpful to understand the sources of disparity to explain why the bias exists. Towards this, we examine the problem of quantifying the contribution of e…

AttributeDecision Making

Disparity-preserved Deep Cross-platform Association for Cross-platform Video Recommendation

2019-01-01 · Shengze Yu, Xin Wang, Wenwu Zhu, Peng Cui 외

Cross-platform recommendation aims to improve recommendation accuracy through associating information from different platforms. Existing cross-platform recommendation approaches assume all cross-platform information to b…