Heterogeneous Graph Transformer
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:BBAEVC2Grecord.jsonopen to challenge →
read the original abstract
Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node- and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations for different types of nodes and edges. To handle dynamic heterogeneous graphs, we introduce the relative temporal encoding technique into HGT, which is able to capture the dynamic structural dependency with arbitrary durations. To handle Web-scale graph data, we design the heterogeneous mini-batch graph sampling algorithm---HGSampling---for efficient and scalable training. Extensive experiments on the Open Academic Graph of 179 million nodes and 2 billion edges show that the proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9%--21% on various downstream tasks.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
TRAVELFRAUDBENCH: A Configurable Evaluation Framework for GNN Fraud Ring Detection in Travel Networks
TravelFraudBench is a new configurable benchmark for GNN-based fraud ring detection in travel networks, simulating star, clique, and chain topologies and showing GraphSAGE outperforming MLP baselines on AUC and ring recovery.
-
Heterogeneous Sheaf Neural Networks
HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduc...
-
Canopy: A Heterograph Foundation Model for Metabolic Engineering
Frozen embeddings from a pretrained heterogeneous graph transformer over a 6.9M-node metabolic-engineering knowledge graph predict fermentation titers at R²=0.41, outperforming tabular baselines (R²=0.24).
-
GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study
GraphLit learns representations from ~20,000 dynamic heterogeneous character networks extracted from Project Gutenberg novels via masked graph autoencoders and outperforms text-only and graph-only baselines on 12 char...
-
Incorporating Deep Learning Design in Database Queries
RelaNN associates tuples with learnable embeddings and lifts relational queries to jointly process data and embeddings, enabling declarative implementation of graph neural networks inside database systems.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.