arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1802.06309cs.LGstat.ML
收藏

学习对抗性的公平和可转移的表示

Learning Adversarially Fair and Transferable Representations

University of Toronto(多伦多大学);Vector Institute(向量研究所)

David Madras, Elliot Creager, Toniann Pitassi, Richard Zemel

摘要:

在本文中,我们提倡表示学习作为减轻下游不公平预测结果的关键。出于一个场景的动机,学习的表示被第三方使用未知的目标,我们提出并探索对抗性表示学习作为一种自然的方法,确保这些方公平行事。我们将群体公平性(人口统计学上的平等、均等化的几率和平等的机会)与不同的对抗性目标联系起来。通过最坏情况下的理论保证和实验验证,我们表明,这个目标的选择是至关重要的公平预测。此外,我们提出了第一个深入的公平迁移学习的实验演示,并实证表明,我们学到的表示承认公平的预测新的任务,同时保持效用,公平表示学习的一个基本目标。

英文摘要:

In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair prediction. Furthermore, we present the first in-depth experimental demonstration of fair transfer learning and demonstrate empirically that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑