activity
20192021
most citedRevisiting Graph Neural Networks: All We Have is Low-Pass Filters

248 citations · 292 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2021

Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters

Takanori Maehara, Hoang NT

Theoretical analyses for graph learning methods often assume a complete observation of the input graph. Such an assumption might not be useful for handling any-size graphs due to t…

cs.LG20202 cited

Stacked Graph Filter

Hoang NT, Takanori Maehara, Tsuyoshi Murata

We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus…

cs.LG20205 cited

Graph Homomorphism Convolution

Hoang NT, Takanori Maehara

In this paper, we study the graph classification problem from the graph homomorphism perspective. We consider the homomorphisms from to , where is a graph of interest (e…

cs.LG201914 cited

A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks

Takanori Maehara, Hoang NT

We present a simple proof for the universality of invariant and equivariant tensorized graph neural networks. Our approach considers a restricted intermediate hypothetical model na…

stat.ML2019248 cited

Revisiting Graph Neural Networks: All We Have is Low-Pass Filters

Hoang NT, Takanori Maehara

Graph neural networks have become one of the most important techniques to solve machine learning problems on graph-structured data. Recent work on vertex classification proposed de…

cs.LG201923 cited

Learning Graph Neural Networks with Noisy Labels

Hoang NT, Choong Jun Jin, Tsuyoshi Murata

We study the robustness to symmetric label noise of GNNs training procedures. By combining the nonlinear neural message-passing models (e.g. Graph Isomorphism Networks, GraphSAGE,…