Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

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



Takanori Maehara , Hoang NT

* The manuscript is accepted as a poster presentation at NeurIPS 2021. This ArXiv version includes the Appendix 

   Access Paper or Ask Questions

Abelian Neural Networks



Kenshin Abe , Takanori Maehara , Issei Sato


   Access Paper or Ask Questions

Stacked Graph Filter



Hoang NT , Takanori Maehara , Tsuyoshi Murata

* Source code is provided at github.com/gear/sgf 

   Access Paper or Ask Questions

Graph Homomorphism Convolution



Hoang NT , Takanori Maehara


   Access Paper or Ask Questions

Tightly Robust Optimization via Empirical Domain Reduction



Akihiro Yabe , Takanori Maehara


   Access Paper or Ask Questions

Learning Directly from Grammar Compressed Text



Yoichi Sasaki , Kosuke Akimoto , Takanori Maehara

* 12 pages, 4 Postscript figures 

   Access Paper or Ask Questions

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



Takanori Maehara , Hoang NT


   Access Paper or Ask Questions

Empirical Hypothesis Space Reduction



Akihiro Yabe , Takanori Maehara


   Access Paper or Ask Questions

Data Cleansing for Models Trained with SGD



Satoshi Hara , Atsushi Nitanda , Takanori Maehara


   Access Paper or Ask Questions

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



Hoang NT , Takanori Maehara

* 12 pages, 5 figures, 2 tables 

   Access Paper or Ask Questions

1
2
3
>>