activity
20152023
most citedRevisiting Graph Neural Networks: All We Have is Low-Pass Filters

248 citations · 339 across the 22 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.DS2020

r-Gathering Problems on Spiders:Hardness, FPT Algorithms, and PTASes

Soh Kumabe, Takanori Maehara

We consider the min-max -gathering problem described as follows: We are given a set of users and facilities in a metric space. We open some of the facilities and assign each use…

cs.LG2020★ 2 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…

math.CO2020

Rank axiom of modular supermatroids: A connection with directional DR submodular functions

Takanori Maehara, So Nakashima

A matroid has been one of the most important combinatorial structures since it was introduced by Whitney as an abstraction of linear independence. As an important property of a mat…

cs.LG2020★ 5 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…

math.OC2020

Tightly Robust Optimization via Empirical Domain Reduction

Akihiro Yabe, Takanori Maehara

Data-driven decision-making is performed by solving a parameterized optimization problem, and the optimal decision is given by an optimal solution for unknown true parameters. We o…

stat.ML2020

Learning Directly from Grammar Compressed Text

Yoichi Sasaki, Kosuke Akimoto, Takanori Maehara

Neural networks using numerous text data have been successfully applied to a variety of tasks. While massive text data is usually compressed using techniques such as grammar compre…