9:00 AM - 9:20 AM
[3G1-GS-2g-01] An Extended Model of Self-Attention Network That Enables Multi-label Node Classification
Keywords:Self-Attention Network, Multi-label Classification, GAT, Node Embedding, Graph Structure Data
For instance, Heterogeneous Graph Attention Network(HAN) can classify a single node label, which uses a Self-Attention Network that takes account of the importance of neighboring nodes. However, it is difficult to obtain high accuracy by simply extending HAN to multi-label classification because some labels are not present in neighboring nodes.
In this study, we propose a multi-label classification method that uses the features obtained by SANNE, which captures a wide range of graph structures from its own nodes, as input for HAN. The effectiveness of the proposed method is demonstrated by applying it to the problem of predicting keywords of papers.
Authentication for paper PDF access
A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.