A Momentum-Based Variance-Reduced Algorithm for Federated Multiobjective Optimization
Not on the map. Why?
Abstract (arXiv)
Federated learning has traditionally been formulated as a single-objective optimization problem, primarily focused on maximizing model utility. In real-world applications, however, machine learning models often need to optimize multiple and potentially conflicting objectives simultaneously. This motivates federated multiobjective optimization (FMOO), which provides a natural framework for jointly handling multiple task-specific objectives in federated learning. In this paper, we propose a momentum-based variance-reduced algorithm for federated multiobjective optimization. The method incorporates a momentum-driven gradient estimator into the local updates to reduce the variance of stochastic updates, leading to an improved convergence rate. We establish theoretical guarantees showing that the expected Pareto stationarity measure of a randomly selected output iterate decays at a rate of O(T-2/3), improving upon the O(T-1/2) rates established for existing methods such as FSMGDA and FedCMOO. Numerical experiments on federated multiobjective optimization benchmarks demonstrate the effectiveness and competitive performance of the proposed algorithm.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 24 Aug 2026.
Builds on
29 of 40 references.
References · 29
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
- 2019Advances and Open Problems in Federated Learningcited by 3,040
- 2018Federated Optimization in Heterogeneous Networkscited by 2,981
- 2020Adaptive Federated Optimizationcited by 1,041
- 2018Multi-Task Learning as Multi-Objective Optimizationcited by 812
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 668
- 2020Personalized Federated Learning with Moreau Envelopescited by 616
- 2021Federated Learning Based on Dynamic Regularizationcited by 559
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 323
- 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
- 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
- 2019Variance Reduced Local SGD with Lower Communication Complexitycited by 80
17 more
- 2021FedCM: Federated Learning with Client-level Momentumcited by 77
- 2019Accelerating Federated Learning via Momentum Gradient Descentcited by 76
- 2023Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscapecited by 46
- 2021STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learningcited by 43
- 2023Momentum Benefits Non-IID Federated Learning Simply and Provablycited by 37
- 2023Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithmscited by 33
- 2021Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learningcited by 31
- 2021A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularizationcited by 27
- 2020Faster On-Device Training Using New Federated Momentum Algorithmcited by 25
- 2023On the Role of Server Momentum in Federated Learningcited by 16
- 2023Federated Multi-Objective Learningcited by 12
- 2022Multi-Label Learning to Rank through Multi-Objective Optimizationcited by 10
- 2020Multi-objective Ranking via Constrained Optimizationcited by 5
- 2024PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimizationcited by 5
- 2024Federated Communication-Efficient Multi-Objective Optimizationcited by 3
- 2024Review of Mathematical Optimization in Federated Learningcited by 3
- 2025Multi-objective methods in Federated Learning: A survey and taxonomycited by 3
Built on by
Not cited yet.