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

2025/05/27 by Mengmeng Chen, Chen, Mengmeng, Xiaohu Wu +13
Computer Science · #Artificial Intelligence (cs.AI) #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2505.20648

openalex publication_date 2025/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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/phnhvvshttps://github.com/buptcmm/phnhvvs.

Citations

• Personalized Federated Learning via Learning Dynamic Graphs
• Ten Challenging Problems in Federated Foundation Models
• Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
• Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learning
• Advances and Open Challenges in Federated Foundation Models
• FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants
• Optimizing the Collaboration Structure in Cross-Silo Federated Learning
• Pareto Set Learning for Expensive Multi-Objective Optimization
• MarS-FL: Enabling Competitors to Collaborate in Federated Learning
• Self-Evolutionary Optimization for Pareto Front Learning
• Federated Multi-Task Learning under a Mixture of Distributions
• Collaboration Equilibrium in Federated Learning
• Scalable Pareto Front Approximation for Deep Multi-Objective Learning
• Exploiting Shared Representations for Personalized Federated Learning
• Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
• Learning Conjoint Attentions for Graph Neural Nets
• Controllable Pareto Multi-Task Learning
• Learning the Pareto Front with Hypernetworks
• Pareto Multi-Task Learning
• Advances and Open Problems in Federated Learning
• Multi-Task Learning as Multi-Objective Optimization
• Dynamic Routing Between Capsules
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Convolutional Neural Networks for Sentence Classification
• Выпуклая оптимизация
• Multidimensional binary search trees used for associative searching
• Gradient-based learning applied to document recognition

Related

• Improving Pareto Front Learning via Multi-Sample Hypernetworks
• Learning the Pareto Front with Hypernetworks
• A Framework for Controllable Pareto Front Learning with Completed Scalarization Functions and its Applications
• Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
• Self-Evolutionary Optimization for Pareto Front Learning