mlsanityData to 14 Oct 2026

Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning

arXiv 2505.20648 ↗First posted 27 May 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-objective optimization (MOO) exists extensively in machine learning, and aims to find a set of Pareto-optimal solutions, called the Pareto front, e.g., it is fundamental for multiple avenues of research in federated learning (FL). Pareto-Front Learning (PFL) is a powerful method implemented using Hypernetworks (PHNs) to approximate the Pareto front. This method enables the acquisition of a mapping function from a given preference vector to the solutions on the Pareto front. However, most existing PFL approaches still face two challenges: (a) sampling rays in high-dimensional spaces; (b) failing to cover the entire Pareto Front which has a convex shape. Here, we introduce a novel PFL framework, called as PHN-HVVS, which decomposes the design space into Voronoi grids and deploys a genetic algorithm (GA) for Voronoi grid partitioning within high-dimensional space. We put forward a new loss function, which effectively contributes to more extensive coverage of the resultant Pareto front and maximizes the HV Indicator. Experimental results on multiple MOO machine learning tasks demonstrate that PHN-HVVS outperforms the baselines significantly in generating Pareto front. Also, we illustrate that PHN-HVVS advances the methodologies of several recent problems in the FL field. The code is available at https://github.com/buptcmm/phnhvvs}{https://github.com/buptcmm/phnhvvs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 71 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

27 of 71 references.

References · 27

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2021Convex optimizationcited by 2,515
  5. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  6. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  7. 2017Dynamic Routing Between Capsulescited by 689
  8. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  9. 2021Towards Personalized Federated Learningcited by 464
  10. 2019Pareto Multi-Task Learningcited by 224
  11. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  12. 2020Learning the Pareto Front with Hypernetworkscited by 125
15 more
  1. 2020Controllable Pareto Multi-Task Learningcited by 51
  2. 2022Pareto Set Learning for Expensive Multi-Objective Optimizationcited by 51
  3. 2021Scalable Pareto Front Approximation for Deep Multi-Objective Learningcited by 45
  4. 2024Advances and Open Challenges in Federated Foundation Modelscited by 36
  5. 2021Learning Conjoint Attentions for Graph Neural Netscited by 26
  6. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  7. 2023Optimizing the Collaboration Structure in Cross-Silo Federated Learningcited by 19
  8. 2021Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximizationcited by 16
  9. 2021Collaboration Equilibrium in Federated Learningcited by 16
  10. 2021MarS-FL: Enabling Competitors to Collaborate in Federated Learningcited by 11
  11. 2024Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learningcited by 9
  12. 2023FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participantscited by 4
  13. 2021Self-Evolutionary Optimization for Pareto Front Learningcited by 3
  14. 2024Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learningcited by 3
  15. 2025Personalized Federated Learning via Learning Dynamic Graphscited by 2

Built on by

Not cited yet.