Do Transformers Really Perform Bad for Graph Representation?

by   Chengxuan Ying, et al.

The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared to mainstream GNN variants. Therefore, it remains a mystery how Transformers could perform well for graph representation learning. In this paper, we solve this mystery by presenting Graphormer, which is built upon the standard Transformer architecture, and could attain excellent results on a broad range of graph representation learning tasks, especially on the recent OGB Large-Scale Challenge. Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model. To this end, we propose several simple yet effective structural encoding methods to help Graphormer better model graph-structured data. Besides, we mathematically characterize the expressive power of Graphormer and exhibit that with our ways of encoding the structural information of graphs, many popular GNN variants could be covered as the special cases of Graphormer.


page 1

page 2

page 3

page 4


Structure-Aware Transformer for Graph Representation Learning

The Transformer architecture has gained growing attention in graph repre...

Gophormer: Ego-Graph Transformer for Node Classification

Transformers have achieved remarkable performance in a myriad of fields ...

Transformer and Snowball Graph Convolution Learning for Biomedical Graph Classification

Graph or network has been widely used for describing and modeling comple...

Relphormer: Relational Graph Transformer for Knowledge Graph Representation

Transformers have achieved remarkable performance in widespread fields, ...

Hierarchical Graph Transformer with Adaptive Node Sampling

The Transformer architecture has achieved remarkable success in a number...

Pure Transformers are Powerful Graph Learners

We show that standard Transformers without graph-specific modifications ...

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

As more deep learning models are being applied in real-world application...

Code Repositories


Graphormer is a deep learning package that allows researchers and developers to train custom models for molecule modeling tasks. It aims to accelerate the research and application in AI for molecule science, such as material discovery, drug discovery, etc.

view repo

Please sign up or login with your details

Forgot password? Click here to reset