Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Jin-Hyun Ahn

Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning

Feb 07, 2022
Jin-Hyun Ahn, Kyungsang Kim, Jeongwan Koh, Quanzheng Li

Figure 1 for Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning

Figure 2 for Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning

Figure 3 for Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning

Figure 4 for Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning

Federated learning (FL) has been intensively investigated in terms of communication efficiency, privacy, and fairness. However, efficient annotation, which is a pain point in real-world FL applications, is less studied. In this project, we propose to apply active learning (AL) and sampling strategy into the FL framework to reduce the annotation workload. We expect that the AL and FL can improve the performance of each other complementarily. In our proposed federated active learning (F-AL) method, the clients collaboratively implement the AL to obtain the instances which are considered as informative to FL in a distributed optimization manner. We compare the test accuracies of the global FL models using the conventional random sampling strategy, client-level separate AL (S-AL), and the proposed F-AL. We empirically demonstrate that the F-AL outperforms baseline methods in image classification tasks.

* 13 pages, 9 figures, submitted for conference publication

Via

Access Paper or Ask Questions

Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

Jul 05, 2019
Jin-Hyun Ahn, Osvaldo Simeone, Joonhyuk Kang

Figure 1 for Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

Figure 2 for Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

Figure 3 for Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

Figure 4 for Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

Cooperative training methods for distributed machine learning typically assume noiseless and ideal communication channels. This work studies some of the opportunities and challenges arising from the presence of wireless communication links. We specifically consider wireless implementations of Federated Learning (FL) and Federated Distillation (FD), as well as of a novel Hybrid Federated Distillation (HFD) scheme. Both digital implementations based on separate source-channel coding and over-the-air computing implementations based on joint source-channel coding are proposed and evaluated over Gaussian multiple-access channels.

* submitted for conference publication

Via

Access Paper or Ask Questions