Timezone: »

 
Spotlight
Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness
Shiyun Lin · Yuze Han · Xiang Li · Zhihua Zhang

Wed Dec 07 09:00 AM -- 11:00 AM (PST) @
in Lightning Talks 3A-1 »

Personalized Federated Learning faces many challenges such as expensive communication costs, training-time adversarial attacks, and performance unfairness across devices. Recent developments witness a trade-off between a reference model and local models to achieve personalization. We follow the avenue and propose a personalized FL method towards the three goals. When it is time to communicate, our method projects local models into a shared-and-fixed low-dimensional random subspace and uses infimal convolution to control the deviation between the reference model and projected local models. We theoretically show our method converges for smooth objectives with square regularizers and the convergence dependence on the projection dimension is mild. We also illustrate the benefits of robustness and fairness on a class of linear problems. Finally, we conduct a large number of experiments to show the empirical superiority of our method over several state-of-the-art methods on the three aspects.

Keywords: Fairness · robustness · communication efficiency · low-dimensional projection · infimal convolution · personalized federated learning

Author Information

Shiyun Lin (Peking University)
Yuze Han (Peking University)
Xiang Li (Peking University)
Zhihua Zhang (Peking University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors