AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

FairMerging: Rethinking Model Merging through the Lens of Fairness

Bing Liu, Xinrui Shan, Boyu Zhang, Qiankun Zhang, Bin Yuan, Jing Wang, Xianjun Deng

ICML 2026 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification

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 Stage 1 sensitivity-control fine-tuning of the target model (ablation)Task Arithmetic · Six-task merging avgfairness gap F(D): 2.14 -> 1.78Improved
add Stage 1 sensitivity-control fine-tuning of the target model (ablation)Ties-Merging · Six-task merging avgfairness gap F(D): 2.11 -> 1.85Improved
add Stage 1 sensitivity-control fine-tuning of the target model (ablation)DARE · Six-task merging avgfairness gap F(D): 2.38 -> 2.17Improved
add Stage 1 sensitivity-control fine-tuning of the target model (ablation)MetaGPT · Six-task merging avgfairness gap F(D): 1.66 -> 1.43Improved
add Stage 1 sensitivity-control fine-tuning of the target model (ablation)AdaMerging · Six-task merging avgfairness gap F(D): 1.49 -> 1.26Improved
add Stage 2 fairness-aware coefficient optimization with orthogonal task vectors (ablation)FairMerging without Stage 1 · Six-task merging avgfairness gap F(D): 1.49 -> 0.58Improved
add Stage 1 on top of Stage 2 (full FairMerging) (ablation)FairMerging Stage 2 · Six-task merging avgfairness gap F(D): 0.58 -> 0.42Improved
replace AdaMerging with full FairMergingAdaMerging · Six-task merging avgfairness gap F(D): 1.49 -> 0.42Improved
replace AdaMerging with full FairMergingAdaMerging · UTK-Facefairness gap F(D): 2.62 -> 0.57Improved
replace AdaMerging with full FairMergingAdaMerging · Six-task merging avgaccuracy (%): 79.25 -> 75.04Hurt
replace Task Arithmetic with full FairMergingTask Arithmetic · Six-task merging avgaccuracy (%): 63.63 -> 75.04Improved

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