http://wd1900.github.io/2019/08/24/Fairness-in-Recommendation-Ranking-through-Pairwise-Comparisons/wd1900.github.io/2019/08/24/Fairness-in-Recommendation-Ranking-through-Pairwise-Comparisons/ 依旧收简历,欢迎各位同学来抖音火山推荐团队,邮箱 wangminghui.wd@bytedance.com 校招可官网投递简历填写内推码...
一方面,以pointwise预测排序方式存在着明显的不足,对于每个物品的预测与最终的ranking之间存在的隔阂;另一方面,推荐系统是始终动态变化的,由于item空间之大、反馈之稀疏,用户与物品是不断变化的,想要对推荐系统的ranking进行评估是很不容易的。对此,本文提出了成对推荐公平指标(pairwise recommendation fairness),主要贡献如...
Fairness and Diversity in the Recommendation and Ranking of Participatory Media ContentMuskaanMehak Preet DhaliwalAaditeshwar Seth
Fairness in recommendation ranking through pairwise comparisons. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019. 2212--2220. Google Scholar [38] Islam R, Keya K N, Zeng Z Q, et al. Debiasing career recommendations with neural ...
Pairwise Fairness Fairness in Recommendation Ranking through Pairwise Comparisons Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Li Wei, Yi Wu, Lukasz Heldt, Zhe Zhao, Lichan Hong, Ed H. Chi, Cristos Goodrow KDD 2019 📒 📝 📷 Strong Demographic Parity Wasserstein Fair Classification...
因此,作者提出Calibrated Recommendation,采用贪心思想生成推荐列表,意图使推荐结果中的物品类别分布与训练数据中接近,而非全部被主要类别占据。需要注意的是这一方法使listwise的,因此可能不便在ranking中使用,而是需要用于rerank环节。 7. Bias Disparity in Recommendation Systems. Tsintzou, Virginia,Pitoura, Evaggelia...
Concretely, we formalize the concepts of ranking-based statistical parity and equal opportunity as two measures of fairness in personalized ranking recommendation for item groups. Then, we empirically show that one of the most widely adopted algorithms -- Bayesian Personalized Ranking -- produces ...
In this paper, we proposed an online re-ranking model named Provider Max-min Fairness Re-ranking (P-MMF) to tackle the problem. Specifically, P-MMF formulates provider fair recommendation as a resource allocation problem, where the exposure slots are considered the resources to be allocated to...
Ranking algorithms are deployed widely to order a set of items in applications such as search engines, news feeds, and recommendation systems. Recent studies, however, have shown that, left unchecked, the output of ranking algorithms can result in decreased diversity in the type of content present...
The minitrack addresses topics related to imposing fairness requirements and conditions in algorithmic decision making. With the introduction of regulations such as GDPR and California algorithms used for automatization of human decision-making in areas such as classification, recommendation, ranking, are ...