Federated Learning with Noisy Labels

08/19/2022
by   Vasileios Tsouvalas, et al.
0

Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets, where the labeling effort is entrusted to the clients. While most existing FL approaches assume high-quality labels are readily available on users' devices; in reality, label noise can naturally occur in FL and follows a non-i.i.d. distribution among clients. Due to the non-iid-ness challenges, existing state-of-the-art centralized approaches exhibit unsatisfactory performance, while previous FL studies rely on data exchange or repeated server-side aid to improve model's performance. Here, we propose FedLN, a framework to deal with label noise across different FL training stages; namely, FL initialization, on-device model training, and server model aggregation. Specifically, FedLN computes per-client noise-level estimation in a single federated round and improves the models' performance by correcting (or limiting the effect of) noisy samples. Extensive experiments on various publicly available vision and audio datasets demonstrate a 24 noise level of 70 human-annotated real-world noisy datasets and report a 9 in models' recognition rate, highlighting that FedLN can be useful for improving FL services provided to everyday users.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset