Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks

12/30/2021
by   Qingsong Lv, et al.
16

Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements. In this work, we present a systematical reproduction of 12 recent HGNNs by using their official codes, datasets, settings, and hyperparameters, revealing surprising findings about the progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN and GAT, are largely underestimated due to improper settings. GAT with proper inputs can generally match or outperform all existing HGNNs across various scenarios. To facilitate robust and reproducible HGNN research, we construct the Heterogeneous Graph Benchmark (HGB), consisting of 11 diverse datasets with three tasks. HGB standardizes the process of heterogeneous graph data splits, feature processing, and performance evaluation. Finally, we introduce a simple but very strong baseline Simple-HGN–which significantly outperforms all previous models on HGB–to accelerate the advancement of HGNNs in the future.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/23/2022

Relation Embedding based Graph Neural Networks for Handling Heterogeneous Graph

Heterogeneous graph learning has drawn significant attentions in recent ...
research
04/07/2023

Rethinking GNN-based Entity Alignment on Heterogeneous Knowledge Graphs: New Datasets and A New Method

The development of knowledge graph (KG) applications has led to a rising...
research
11/13/2019

On the choice of graph neural network architectures

Seminal works on graph neural networks have primarily targeted semi-supe...
research
05/31/2023

Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popu...
research
04/06/2022

How Do Graph Networks Generalize to Large and Diverse Molecular Systems?

The predominant method of demonstrating progress of atomic graph neural ...
research
02/18/2022

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

Heterogeneous Graph Neural Network (HGNN) has been successfully employed...
research
11/30/2020

Graph convolutions that can finally model local structure

Despite quick progress in the last few years, recent studies have shown ...

Please sign up or login with your details

Forgot password? Click here to reset