| 研究実績の概要 |
We have achieved four main outcomes. a) We proposed a new GNN model for robust predictions irrespective of the presence or absence of noise in edges, nodes, or both. This work has been accepted by PAKDD-2024. b) We proposed a continuous-time dynamic graph learning model to detect potential real-time donations in YouTube live streaming services. This work has been published in Machine Learning journal. c) We introduced an advanced multi-layer temporal graph neural network framework to learn entity representations and predict trends in social media. This work has been published in Complex & Intelligent Systems journal. d) We presented a knowledge graph embedding-based method for automatically predicting missing human biography records in Wikipedia. This work has been published in ECAI-2024.
|
