Fair Resource Allocation in Federated Learning

Abstract

Federated learning involves training statistical models in massive, heterogeneous networks. Naively minimizing an aggregate loss function in such a network may disproportionately advantage or disadvantage some of the devices. In this work, we propose q-Fair Federated Learning (q-FFL), a novel optimization objective inspired by fair resource allocation in wireless networks that encourages a more fair (specifically, a more uniform) accuracy distribution across devices in federated networks. To solve q-FFL, we devise a communication-efficient method, q-FedAvg, that is suited to federated networks. We validate both the effectiveness of q-FFL and the efficiency of q-FedAvg on a suite of federated datasets with both convex and non-convex models, and show that q-FFL (along with q-FedAvg) outperforms existing baselines in terms of the resulting fairness, flexibility, and efficiency.

ICLR 2020

References in corpus (11)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Equality of Opportunity in Supervised Learning
• Communication Efficient Distributed Optimization using an Approximate Newton-type Method
• LEAF: A Benchmark for Federated Settings
• Agnostic Federated Learning
• Fairness Without Demographics in Repeated Loss Minimization
• Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
• Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
• A Characterization of Guesswork on Swiftly Tilting Curves

Cited by in corpus (65)

• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
• SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
• Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
• Personalized Federated Learning: A Meta-Learning Approach
• From Distributed Machine Learning to Federated Learning: A Survey
• FedML: A Research Library and Benchmark for Federated Machine Learning
• LEAF: A Benchmark for Federated Settings
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• On the Convergence of Local Descent Methods in Federated Learning
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Flower: A Friendly Federated Learning Research Framework
• Survey on Machine Learning for Traffic-Driven Service Provisioning in Optical Networks
• Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
• Improving Fairness for Data Valuation in Horizontal Federated Learning
• FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
• Federated Learning for Healthcare Informatics
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
• Federated Learning for Big Data: A Survey on Opportunities, Applications, and Future Directions
• Hierarchically Fair Federated Learning
• A Systematic Literature Review on Client Selection in Federated Learning
• Local Differential Privacy based Federated Learning for Internet of Things
• Fairness and Accuracy in Federated Learning
• Multi-Model Federated Learning
• Graph Federated Learning for CIoT Devices in Smart Home Applications
• Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning
• FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion
• Federated brain tumor segmentation: an extensive benchmark
• FedEval: A Holistic Evaluation Framework for Federated Learning
• Training Fair Models in Federated Learning without Data Privacy Infringement
• FedSynthCT-Brain: A Federated Learning Framework for Multi-Institutional Brain MRI-to-CT Synthesis
• Federated Learning for Clinical Structured Data: A Benchmark Comparison of Engineering and Statistical Approaches
• Device Heterogeneity in Federated Learning: A Superquantile Approach
• Federated Learning with Superquantile Aggregation for Heterogeneous Data
• Optimality and Stability in Federated Learning: A Game-theoretic Approach
• Sustainable Federated Learning
• Applications of Federated Learning in Smart Cities: Recent Advances, Taxonomy, and Open Challenges
• Byzantine-Resilient Secure Federated Learning
• FLEdge: Benchmarking Federated Machine Learning Applications in Edge Computing Systems
• Federated Mixture of Experts
• Heterogeneous Data-Aware Federated Learning
• Toward an Automated Auction Framework for Wireless Federated Learning Services Market
• Wireless for Machine Learning
• Loss Tolerant Federated Learning
• Auxo: Efficient Federated Learning via Scalable Client Clustering
• Towards Fair Federated Learning with Zero-Shot Data Augmentation
• Federated Edge Learning : Design Issues and Challenges
• Privacy-preserving Federated Bayesian Learning of a Generative Model for Imbalanced Classification of Clinical Data
• Bandwidth Allocation for Multiple Federated Learning Services in Wireless Edge Networks
• Anarchic Federated Learning
• Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy
• Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning
• FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction
• Federated Learning with Fair Averaging
• Asynchronous Federated Learning for Sensor Data with Concept Drift
• FedGPO: Heterogeneity-Aware Global Parameter Optimization for Efficient Federated Learning
• Representation of Federated Learning via Worst-Case Robust Optimization Theory
• New Metrics to Evaluate the Performance and Fairness of Personalized Federated Learning
• Demystifying the Effects of Non-Independence in Federated Learning
• Unsupervised Learning of Debiased Representations with Pseudo-Attributes
• GRAFFL: Gradient-free Federated Learning of a Bayesian Generative Model
• Fair for All: Best-effort Fairness Guarantees for Classification
• Collaborative and Federated Black-box Optimization: A Bayesian Optimization Perspective
• Management of Resource at the Network Edge for Federated Learning
• On the Fairness of Swarm Learning in Skin Lesion Classification