Oct 17, 2020 · Artificial Intelligence

DyHAN: Dynamic Heterogeneous Graph Embedding with Hierarchical Attention

This article introduces DyHAN, a dynamic heterogeneous graph embedding method that employs hierarchical attention across node, edge, and temporal dimensions to capture evolving user-item interactions, demonstrates superior performance over static and existing dynamic baselines, and reports significant online improvements in Alibaba’s recommendation system.

AlibabaAttention Mechanismdynamic graphs

0 likes · 9 min read

DyHAN: Dynamic Heterogeneous Graph Embedding with Hierarchical Attention

Alibaba Cloud Developer

Aug 9, 2019 · Artificial Intelligence

How GATNE Advances Heterogeneous Graph Embedding with Edge Types and Node Features

This article introduces GATNE, a graph embedding framework that jointly models heterogeneous nodes, multiple edge types, and rich node attributes using base and edge embeddings, self‑attention, and inductive learning, and demonstrates its superior performance on several real‑world datasets.

GATNESelf-Attentiongraph embedding

0 likes · 8 min read

How GATNE Advances Heterogeneous Graph Embedding with Edge Types and Node Features