5 citations · 7 across the 6 of their papers we have counts for
6 papers
Compositionality-Aware Graph2Seq Learning
Takeshi D. Itoh, Takatomi Kubo, Kazushi Ikeda
Graphs are a highly expressive data structure, but it is often difficult for humans to find patterns from a complex graph. Hence, generating human-interpretable sequences from grap…
Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
Takeshi D. Itoh, Takatomi Kubo, Kazushi Ikeda
Graph neural networks (GNNs) have been widely used to learn vector representation of graph-structured data and achieved better task performance than conventional methods. The found…
Detecting Unknown Behaviors by Pre-defined Behaviours: An Bayesian Non-parametric Approach
Jin Watanabe, Takatomi Kubo, Fan Yang +1
An automatic mouse behavior recognition system can considerably reduce the workload of experimenters and facilitate the analysis process. Typically, supervised approaches, unsuperv…
A Hierarchical Mixture Density Network
Fan Yang, Jaymar Soriano, Takatomi Kubo +1
The relationship among three correlated variables could be very sophisticated, as a result, we may not be able to find their hidden causality and model their relationship explicitl…
Towards Generation of Visual Attention Map for Source Code
Takeshi D. Itoh, Takatomi Kubo, Kiyoka Ikeda +5
Program comprehension is a dominant process in software development and maintenance. Experts are considered to comprehend the source code efficiently by directing their gaze, or at…
Toward Imitating Visual Attention of Experts in Software Development Tasks
Yoshiharu Ikutani, Nishanth Koganti, Hideaki Hata +2
Expert programmers' eye-movements during source code reading are valuable sources that are considered to be associated with their domain expertise. We advocate a vision of new inte…