Practical Distributed Learning: Secure Machine Learning with Communication-Efficient Local Updates

By Cong Xie, Oluwasanmi Koyejo, Indranil Gupta. 2019

14 citations recorded by the source corpus.

Federated learning on edge devices poses new challenges arising from workers that misbehave, privacy needs, etc. We propose a new robust federated optimization algorithm, with provable convergence and robustness under non-IID settings. Empirical results show that the proposed algorithm stabilizes the convergence and tolerates data poisoning on a small number of workers.

Subfields: Federated & Distributed Learning, Privacy & Security

How researchers see this paper

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

In Federated & Distributed Learning

1. Jy-yong Sohn
2. Hongyi Wang
3. Shashank Rajput
4. Xu Chen
5. Dusist Niyato
6. Dimitris Papailiopoulos
7. Xiaofei Wang
8. Saurabh Agarwal

In Privacy & Security

1. Victor C. M. Leung
2. Dusist Niyato
3. Dimitris Papailiopoulos
4. Hongyi Wang

Citations in the corpus

• Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020, background): “Across most FL settings, it is assumed that there is no single, central authority that owns or verifies the training data or user hardware, and it has been argued by many recent studies that FL lends itself to new adversarial attacks during decentralized model training [12, 13, 14, 15, 16, 17, 18, 1”
• Robust Federated Recommendation System (2020, methodology): “, utilize the model parameters among clients to detect Byzantine clients [7; 11; 23; 41; 21].”
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2019, background): “To make FL capable of tolerating a small number of devices training on the poisoned dataset, robust federated optimization [201] defines a trimmed mean oper-”