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

By Chaoyang He, Conghui Tan, Hanlin Tang, Shuang Qiu, Ji Liu. 2019

80 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Science and Operations Research, Federated & Distributed Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Federated & Distributed Learning

Citations in the corpus

Advances and Open Problems in Federated Learning (2019, background): “Extending FL to other ML paradigms, including reinforcement learning, semisupervised and unsupervised learning, active learning, and online learning [200, 435] all present interesting and open challenges.”
FedML: A Research Library and Benchmark for Federated Machine Learning (2020, methodology): “We use [43], a central server free FL algorithm, to demonstrate how FedML supports decentralized topology with directed communication.”
FedNAS: Federated Deep Learning via Neural Architecture Search (2020, methodology): “While in the Fed-erated Learning (FL) domain [9, 2], using designed model architectures and optimizing by FedAvg [9] is the main method to improve model performance.”
Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning (2020, background): “More recently, decentralized federated learning architectures without a central server have been considered for peer-topeer learning on graph topologies [15] and in the context of social networks [16].”
Group Knowledge Transfer: Collaborative Training of Large CNNs on the Edge (2020, background): “FL is a distributed learning paradigm that can collaboratively train a common model for many edge devices without centralizing any device’s dataset [6, 7, 8].”
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge (2020, background): “FL is a distributed learning paradigm that can collaboratively train a global model for many edge devices without centralizing any device’s dataset [6, 7, 8].”
Federated Learning for Healthcare Informatics (2019, background): “Therefore, some researches began to study fully decentralized framework where the central server is not required [41, 60, 85, 91].”
From distributed machine learning to federated learning: a survey (2021, background): “3) are also proposed to deal with the decentralized graph data for social network [67] and drug discovery [63].”
Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, methodology): “In [126], the authors propose a serverfree decentralized federated learning approach based on an online Push-Sum algorithm.”
Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search. (2020, methodology): “While in the Federated Learning (FL) domain [10, 3], using designed model architectures and optimizing by FedAvg [10] is the main method to improve model performance.”
Decentralized Federated Learning: A Survey and Perspective (2023, background): “He et al. [50] addressed trust issues between clients by employing an online push-sum algorithm to actively push local models to trusted clients.”