Timezone: »

FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning
Tao Qi · Fangzhao Wu · Chuhan Wu · Lingjuan Lyu · Tong Xu · Hao Liao · Zhongliang Yang · Yongfeng Huang · Xing Xie

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #1041

Vertical federated learning (VFL) is a privacy-preserving machine learning paradigm that can learn models from features distributed on different platforms in a privacy-preserving way. Since in real-world applications the data may contain bias on fairness-sensitive features (e.g., gender), VFL models may inherit bias from training data and become unfair for some user groups. However, existing fair machine learning methods usually rely on the centralized storage of fairness-sensitive features to achieve model fairness, which are usually inapplicable in federated scenarios. In this paper, we propose a fair vertical federated learning framework (FairVFL), which can improve the fairness of VFL models. The core idea of FairVFL is to learn unified and fair representations of samples based on the decentralized feature fields in a privacy-preserving way. Specifically, each platform with fairness-insensitive features first learns local data representations from local features. Then, these local representations are uploaded to a server and aggregated into a unified representation for the target task. In order to learn a fair unified representation, we send it to each platform storing fairness-sensitive features and apply adversarial learning to remove bias from the unified representation inherited from the biased data. Moreover, for protecting user privacy, we further propose a contrastive adversarial learning method to remove private information from the unified representation in server before sending it to the platforms keeping fairness-sensitive features. Experiments on three real-world datasets validate that our method can effectively improve model fairness with user privacy well-protected.

Author Information

Tao Qi (Tsinghua University, Tsinghua University)
Fangzhao Wu
Chuhan Wu (Tsinghua University)
Lingjuan Lyu (Sony AI)
Tong Xu (University of Science and Technology of China)
Hao Liao (Shenzhen University)
Zhongliang Yang (Tsinghua University, Tsinghua University)
Yongfeng Huang (Tsinghua University, Tsinghua University)
Xing Xie (Microsoft Research Asia)

More from the Same Authors