most citedOvercoming Forgetting in Federated Learning on Non-IID Data

143 citations · 143 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2021

An Exploration into why Output Regularization Mitigates Label Noise

Neta Shoham, Tomer Avidor, Nadav Israel

Label noise presents a real challenge for supervised learning algorithms. Consequently, mitigating label noise has attracted immense research in recent years. Noise robust losses i…

cs.LG2019★ 143 cited

Overcoming Forgetting in Federated Learning on Non-IID Data

Neta Shoham, Tomer Avidor, Aviv Keren +4

We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt…