Central Server Free Federated Learning over Single-sided Trust Social Networks

Abstract

Federated learning has become increasingly important for modern machine learning, especially for data privacy-sensitive scenarios. Existing federated learning mostly adopts the central server-based architecture or centralized architecture. However, in many social network scenarios, centralized federated learning is not applicable (e.g., a central agent or server connecting all users may not exist, or the communication cost to the central server is not affordable). In this paper, we consider a generic setting: 1) the central server may not exist, and 2) the social network is unidirectional or of single-sided trust (i.e., user A trusts user B but user B may not trust user A). We propose a central server free federated learning algorithm, named Online Push-Sum (OPS) method, to handle this challenging but generic scenario. A rigorous regret analysis is also provided, which shows very interesting results on how users can benefit from communication with trusted users in the federated learning scenario. This work builds upon the fundamental algorithm framework and theoretical guarantees for federated learning in the generic social network scenario.

arXiv commentdecentralized federated learning

References in corpus (16)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Federated Optimization:Distributed Optimization Beyond the Datacenter
• FedML: A Research Library and Benchmark for Federated Machine Learning
• Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
• Don't Use Large Mini-Batches, Use Local SGD
• Local SGD Converges Fast and Communicates Little
• Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
• Communication-Efficient Distributed Dual Coordinate Ascent
• Decentralized Collaborative Learning of Personalized Models over Networks
• CoCoA: A General Framework for Communication-Efficient Distributed Optimization
• Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training
• Personalized and Private Peer-to-Peer Machine Learning
• Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
• Analysis of Distributed Stochastic Dual Coordinate Ascent

Cited by in corpus (18)

• FedML: A Research Library and Benchmark for Federated Machine Learning
• Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
• Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
• A Field Guide to Federated Optimization
• FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
• Federated Learning for Healthcare Informatics
• Communication Efficiency in Federated Learning: Achievements and Challenges
• The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
• FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
• Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI
• Multi-consensus Decentralized Accelerated Gradient Descent
• Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning
• Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search
• BAFFLE : Blockchain Based Aggregator Free Federated Learning
• GFL: A Decentralized Federated Learning Framework Based On Blockchain
• Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent
• Real-Time Decentralized knowledge Transfer at the Edge
• The Effect of Training Parameters and Mechanisms on Decentralized Federated Learning based on MNIST Dataset