Research map / Learning theory and algorithms / Fairness
From Gradient Volume to Shapley Fairness: Towards Fair Multi-Task Learning
Xiao Wang, Yuying Han, Dazi Li, Fei Zhang, Min Tang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Shapley-value weights from VolDet to loss-based RLW (ablation) | RLW · NYU-v2 | Delta m%: 7.78 -> 7.60 | Improved |
| add Shapley-value weights from VolDet to DWA (ablation) | DWA · NYU-v2 | Delta m%: 3.57 -> 2.17 | Improved |
| add Shapley-value weights from VolDetPro to UW (ablation) | UW · NYU-v2 | Delta m%: 4.05 -> -1.50 | Improved |
| replace FairGrad weights with Shapley-VolDet weights | SVFair · NYU-v2 | Delta m%: -4.66 -> -8.81 | Improved |
| use SVFair instead of PIVRG | SVFair · Cityscapes | Mean Rank: MR 2.50 (PIVRG) vs 6.88 (VolDet); Delta m% -0.45 vs -2.08 | Mixed |
| use VolDetPro instead of VolDet (ablation) | SVFair · Office-31 | Delta m%: -1.53 -> -1.62 | Improved |
| use VolDetPro instead of VolDet (ablation) | SVFair · CelebA | Delta m%: -0.63 -> 0.11 | Hurt |
| increase temperature tau from 1.0 to 5.0 (ablation) | SVFair(VolDet) · Cityscapes | Delta m%: 0.10 -> -2.16 | Improved |
| increase temperature tau from 0.5 to 5.0 (ablation) | SVFair(VolDet) · Office-31 | Delta m%: -1.49 -> -0.97 | Hurt |
| add Monte Carlo Shapley estimation with K=1k to SVFair on CelebA | SVFair · CelebA | single-epoch runtime (s): 810 -> 870 (K=1k); 1086 (K=5k) | Hurt |
Closest papers by meaning
- Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction (CVPR 2025 · similarity 0.89)
- Fair Resource Allocation in Multi-Task Learning (ICML 2024 · similarity 0.89)
- FairMT: Fairness for Heterogeneous Multi-Task Learning (NeurIPS 2026 · similarity 0.87)
- FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning (NeurIPS 2025 · similarity 0.85)
- Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters (CVPR 2025 · similarity 0.85)
- Fairness-Aware Meta-Learning via Nash Bargaining (NeurIPS 2024 · similarity 0.84)
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.
