On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction

no code implementations • 17 Oct 2023 • Seohyeon Cha, Honggu Kang, Joonhyuk Kang

Building on a recent work that introduced a scaling parameter for constructing valid credible regions from posterior estimate, our study explores the advantages of incorporating a temperature parameter into Bayesian GNNs within CP framework.

Conformal Prediction Uncertainty Quantification +1

NeFL: Nested Federated Learning for Heterogeneous Clients

no code implementations • 15 Aug 2023 • Honggu Kang, Seohyeon Cha, Jinwoo Shin, Jongmyeong Lee, Joonhyuk Kang

Previous studies tackle the system heterogeneity by splitting a model into submodels, but with less degree-of-freedom in terms of model architecture.

Federated Learning