activity
20172020
most citedGraph Residual Flow for Molecular Graph Generation

31 citations · 64 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG202020 cited

Universal Approximation Property of Neural Ordinary Differential Equations

Takeshi Teshima, Koichi Tojo, Masahiro Ikeda +2

Neural ordinary differential equations (NODEs) is an invertible neural network architecture promising for its free-form Jacobian and the availability of a tractable Jacobian determ…

cs.LG2020

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

Takeshi Teshima, Isao Ishikawa, Koichi Tojo +3

Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirabl…

cs.LG2020

Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks

Kenta Oono, Taiji Suzuki

It is known that the current graph neural networks (GNNs) are difficult to make themselves deep due to the problem known as over-smoothing. Multi-scale GNNs are a promising approac…

cs.LG20202 cited

Weisfeiler-Lehman Embedding for Molecular Graph Neural Networks

Katsuhiko Ishiguro, Kenta Oono, Kohei Hayashi

A graph neural network (GNN) is a good choice for predicting the chemical properties of molecules. Compared with other deep networks, however, the current performance of a GNN is l…

cs.LG201931 cited

Graph Residual Flow for Molecular Graph Generation

Shion Honda, Hirotaka Akita, Katsuhiko Ishiguro +2

Statistical generative models for molecular graphs attract attention from many researchers from the fields of bio- and chemo-informatics. Among these models, invertible flow-based…

cs.LG2019

Graph Neural Networks Exponentially Lose Expressive Power for Node Classification

Kenta Oono, Taiji Suzuki

Graph Neural Networks (graph NNs) are a promising deep learning approach for analyzing graph-structured data. However, it is known that they do not improve (or sometimes worsen) th…