1 code implementation • 11 Dec 2021 • Nuttapong Chairatanakul, Hoang NT, Xin Liu, Tsuyoshi Murata
Different from the popular recurrent modeling approach, we propose a new solution named LeapRec to the temporal dynamic problem by using trajectory-based meta-learning to model time dependencies.
no code implementations • NeurIPS 2021 • Takanori Maehara, Hoang NT
Theoretical analyses for graph learning methods often assume a complete observation of the input graph.
no code implementations • 1 Jan 2021 • 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 trainable polynomial coefficients.
1 code implementation • 22 Nov 2020 • 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 trainable polynomial coefficients.
1 code implementation • ICML 2020 • Hoang NT, Takanori Maehara
In this paper, we study the graph classification problem from the graph homomorphism perspective.
no code implementations • 9 Oct 2019 • Takanori Maehara, Hoang NT
We present a simple proof for the universality of invariant and equivariant tensorized graph neural networks.
no code implementations • 25 Sep 2019 • Hoang NT, Takanori Maehara
In this work, we develop quantitative results to the learnablity of a two-layers Graph Convolutional Network (GCN).
2 code implementations • 23 May 2019 • Hoang NT, Takanori Maehara
However, we find that the feature vectors of benchmark datasets are already quite informative for the classification task, and the graph structure only provides a means to denoise the data.
no code implementations • ICLR Workshop LLD 2019 • Hoang NT, Choong Jun Jin, Tsuyoshi Murata
We study the robustness to symmetric label noise of GNNs training procedures.