Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.05424 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908499901939712 |
|---|---|
| author | Rao, Jiansheng Li, Jiayi Gong, Zhizhi Kar, Soummya Li, Haoxuan |
| author_facet | Rao, Jiansheng Li, Jiayi Gong, Zhizhi Kar, Soummya Li, Haoxuan |
| contents | Federated learning (FL) is a widely adopted paradigm for privacy-preserving model training, but FedAvg optimise for the majority while under-serving minority clients. Existing methods such as federated multi-objective learning (FMOL) attempts to import multi-objective optimisation (MOO) into FL. However, it merely delivers task-wise Pareto-stationary points, leaving client fairness to chance. In this paper, we introduce Conically-Regularised FMOL (CR-FMOL), the first federated MOO framework that enforces client-wise Pareto optimality through a novel preference-cone constraint. After local federated multi-gradient descent averaging (FMGDA) / federated stochastic multi-gradient descent averaging (FSMGDA) steps, each client transmits its aggregated task-loss vector as an implicit preference; the server then solves a cone-constrained Pareto-MTL sub-problem centred at the uniform vector, producing a descent direction that is Pareto-stationary for every client within its cone. Experiments on non-IID benchmarks show that CR-FMOL enhances client fairness, and although the early-stage performance is slightly inferior to FedAvg, it is expected to achieve comparable accuracy given sufficient training rounds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05424 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated Multi-Objective Learning with Controlled Pareto Frontiers Rao, Jiansheng Li, Jiayi Gong, Zhizhi Kar, Soummya Li, Haoxuan Machine Learning Federated learning (FL) is a widely adopted paradigm for privacy-preserving model training, but FedAvg optimise for the majority while under-serving minority clients. Existing methods such as federated multi-objective learning (FMOL) attempts to import multi-objective optimisation (MOO) into FL. However, it merely delivers task-wise Pareto-stationary points, leaving client fairness to chance. In this paper, we introduce Conically-Regularised FMOL (CR-FMOL), the first federated MOO framework that enforces client-wise Pareto optimality through a novel preference-cone constraint. After local federated multi-gradient descent averaging (FMGDA) / federated stochastic multi-gradient descent averaging (FSMGDA) steps, each client transmits its aggregated task-loss vector as an implicit preference; the server then solves a cone-constrained Pareto-MTL sub-problem centred at the uniform vector, producing a descent direction that is Pareto-stationary for every client within its cone. Experiments on non-IID benchmarks show that CR-FMOL enhances client fairness, and although the early-stage performance is slightly inferior to FedAvg, it is expected to achieve comparable accuracy given sufficient training rounds. |
| title | Federated Multi-Objective Learning with Controlled Pareto Frontiers |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.05424 |