H
Houye Ji
Researcher at Beijing University of Posts and Telecommunications
Publications - 14
Citations - 1959
Houye Ji is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Graph (abstract data type) & Deep learning. The author has an hindex of 6, co-authored 13 publications receiving 736 citations.
Papers
More filters
Proceedings ArticleDOI
Heterogeneous Graph Attention Network
TL;DR: Wang et al. as discussed by the authors proposed a heterogeneous graph neural network based on the hierarchical attention, including node-level and semantic-level attentions, which can generate node embedding by aggregating features from meta-path based neighbors in a hierarchical manner.
Journal ArticleDOI
HGAT: Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification
TL;DR: A novel heterogeneous graph neural network-based method for semi-supervised short text classification, leveraging full advantage of limited labeled data and large unlabeled data through information propagation along the graph.
Proceedings ArticleDOI
Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification
TL;DR: A novel heterogeneous graph neural network based method for semi-supervised short text classification, leveraging full advantage of few labeled data and large unlabeled data through information propagation along the graph is proposed.
Proceedings ArticleDOI
Interpreting and Unifying Graph Neural Networks with An Optimization Framework
TL;DR: In this paper, a unified optimization framework is proposed for GNNs, which summarizes the commonalities between several representative GNN architectures and provides a macroscopic view on surveying the relations between different architectures, and further opens up new opportunities for flexibly designing new architectures.
Journal ArticleDOI
Heterogeneous Graph Propagation Network
TL;DR: This work proposes a novel Heterogeneous graph Propagation Network (HPN), which improves the node-level aggregating process via absorbing node’s local semantic with a proper weight, which makes HPN capture the characteristics of each node and learn distinguishable node embedding with deeper HeteGNN architecture.