E
Eunyee Koh
Researcher at Adobe Systems
Publications - 110
Citations - 1855
Eunyee Koh is an academic researcher from Adobe Systems. The author has contributed to research in topics: Graph (abstract data type) & Visualization. The author has an hindex of 18, co-authored 104 publications receiving 1226 citations. Previous affiliations of Eunyee Koh include Texas A&M University & Intel.
Papers
More filters
Proceedings ArticleDOI
Continuous-Time Dynamic Network Embeddings
TL;DR: The proposed framework gives rise to methods for learning time-respecting embeddings from continuous-time dynamic networks and indicates that modeling temporal dependencies in graphs is important for learning appropriate and meaningful network representations.
Journal ArticleDOI
Attention Models in Graphs: A Survey
TL;DR: This work conducts a comprehensive and focused survey of the literature on the emerging field of graph attention models and introduces three intuitive taxonomies to group existing work.
Proceedings ArticleDOI
Higher-order Network Representation Learning
TL;DR: The experimental results demonstrate the effectiveness of learning higher-order network representations with a mean relative gain in AUC of 19% across a wide variety of networks and embedding methods.
Posted Content
Attention Models in Graphs: A Survey
TL;DR: This work conducts a comprehensive and focused survey of the literature on the emerging field of graph attention models and introduces three intuitive taxonomies to group existing work.
Proceedings ArticleDOI
Graph Convolutional Networks with Motif-based Attention
TL;DR: This work proposes a motif-based graph attention model, called Motif Convolutional Networks, which generalizes past approaches by using weighted multi-hop motif adjacency matrices to capture higher-order neighborhoods.