Debiasing Neural Retrieval via In-batch Balancing Regularization

May 18, 2022 Β· Declared Dead Β· πŸ› GEBNLP

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yuantong Li, Xiaokai Wei, Zijian Wang, Shen Wang, Parminder Bhatia, Xiaofei Ma, Andrew Arnold arXiv ID 2205.09240 Category cs.IR: Information Retrieval Cross-listed cs.AI, cs.CY Citations 4 Venue GEBNLP Last Checked 4 months ago
Abstract
People frequently interact with information retrieval (IR) systems, however, IR models exhibit biases and discrimination towards various demographics. The in-processing fair ranking methods provide a trade-offs between accuracy and fairness through adding a fairness-related regularization term in the loss function. However, there haven't been intuitive objective functions that depend on the click probability and user engagement to directly optimize towards this. In this work, we propose the In-Batch Balancing Regularization (IBBR) to mitigate the ranking disparity among subgroups. In particular, we develop a differentiable \textit{normed Pairwise Ranking Fairness} (nPRF) and leverage the T-statistics on top of nPRF over subgroups as a regularization to improve fairness. Empirical results with the BERT-based neural rankers on the MS MARCO Passage Retrieval dataset with the human-annotated non-gendered queries benchmark \citep{rekabsaz2020neural} show that our IBBR method with nPRF achieves significantly less bias with minimal degradation in ranking performance compared with the baseline.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted