AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

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

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Vertical federated learning · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add adversarial fairness learning (FairVFL) to VFLVFL with MLP · ADULTgender attacker F1 (lower = fairer): 79.05 -> 50.31Improved
add adversarial fairness learning (FairVFL) to VFLVFL with MLP · ADULTaccuracy: 81.47 -> 76.74Hurt
add adversarial fairness learning (FairVFL) to VFLVFL with NAML · NEWSgender attacker F1 (lower = fairer): 69.72 -> 53.38Improved
add adversarial fairness learning (FairVFL) to VFLVFL with NAML · NEWSAUC: 63.93 -> 60.41Hurt
add adversarial fairness learning (FairVFL) to VFLVFL ResNet-10 · CelebAgender attacker F1 (lower = fairer): 0.8727 -> 0.5143Improved
vertical federated training instead of centralized trainingMLP/NAML · ADULT, NEWSaccuracy / AUC: 82.15 -> 81.47 (ADULT MLP accuracy)No clear effect
federated FairVFL instead of centralized fair methods (FairGo etc.)MLP · ADULTaccuracy / gender F1: 77.97 -> 76.74 accuracy; 50.92 -> 50.31 gender F1No clear effect
add adversarial learning on gender discrimination (ablation)FairVFL · ADULTgender attacker F1 (lower = fairer)Improved
add adversarial learning on age discrimination (ablation)FairVFL · ADULTage attacker F1 (lower = fairer)Improved
add contrastive adversarial learning on shared representations (ablation)FairVFL · ADULTprivacy attack F1 (lower = more private)Improved
increase contrastive adversarial weight gamma_c (ablation)FairVFL · ADULTprivacy protection vs fairnessMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy