Timezone: »

SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
Enmao Diao · Jie Ding · Vahid Tarokh

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #204

Federated Learning allows the training of machine learning models by using the computation and private data resources of many distributed clients. Most existing results on Federated Learning (FL) assume the clients have ground-truth labels. However, in many practical scenarios, clients may be unable to label task-specific data due to a lack of expertise or resource. We propose SemiFL to address the problem of combining communication-efficient FL such as FedAvg with Semi-Supervised Learning (SSL). In SemiFL, clients have completely unlabeled data and can train multiple local epochs to reduce communication costs, while the server has a small amount of labeled data. We provide a theoretical understanding of the success of data augmentation-based SSL methods to illustrate the bottleneck of a vanilla combination of communication-efficient FL with SSL. To address this issue, we propose alternate training to 'fine-tune global model with labeled data' and 'generate pseudo-labels with the global model.' We conduct extensive experiments and demonstrate that our approach significantly improves the performance of a labeled server with unlabeled clients training with multiple local epochs. Moreover, our method outperforms many existing SSFL baselines and performs competitively with the state-of-the-art FL and SSL results.

Author Information

Enmao Diao (Duke University)
Enmao Diao

I am a fourth-year Ph.D. candidate advised by Prof. Vahid Tarokh in Electrical Engineering at Duke University, Durham, North Carolina, USA. I was born in Chengdu, Sichuan, China in 1994. I received the B.S. degree in Computer Science and Electrical Engineering from Georgia Institute of Technology, Georgia, USA, in 2016 and the M.S. degree in Electrical Engineering from Harvard University, Cambridge, USA, in 2018.

Jie Ding (University of Minnesota)
Vahid Tarokh (Duke University)

More from the Same Authors