3 papers
cs.LG2026
Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
Hiroki Naganuma, Taiji Suzuki, Rio Yokota +3
Generalization measures have been studied extensively in the machine learning community to better characterize generalization gaps. However, establishing a reliable generalization…
cs.LG2023
Scalable Federated Learning for Clients with Different Input Image Sizes and Numbers of Output Categories
Shuhei Nitta, Taiji Suzuki, Albert Rodríguez Mulet +2
Federated learning is a privacy-preserving training method which consists of training from a plurality of clients but without sharing their confidential data. However, previous wor…
cs.LG2022
Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs
Kishan Wimalawarne, Taiji Suzuki
We investigate efficient learning from higher-order graph convolution and learning directly from adjacency matrices for node classification. We revisit the scaled graph residual ne…