16 citations · 16 across the 4 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024
Re-evaluating Group Robustness via Adaptive Class-Specific Scaling
Seonguk Seo, Bohyung Han
Group distributionally robust optimization, which aims to improve robust accuracies -- worst-group and unbiased accuracies -- is a prominent algorithm used to mitigate spurious cor…
cs.LG2024
Relaxed Contrastive Learning for Federated Learning
Seonguk Seo, Jinkyu Kim, Geeho Kim +1
We propose a novel contrastive learning framework to effectively address the challenges of data heterogeneity in federated learning. We first analyze the inconsistency of gradient…
cs.LG2022★ 16 cited
Communication-Efficient Federated Learning with Accelerated Client Gradient
Geeho Kim, Jinkyu Kim, Bohyung Han
Federated learning often suffers from slow and unstable convergence due to the heterogeneous characteristics of participating client datasets. Such a tendency is aggravated when th…