Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs

About

The graph Transformer emerges as a new architecture and has shown superior performance on various graph mining tasks. In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence composed of all node tokens so as to train the Transformer model, causing it hard to scale to large graphs due to the quadratic complexity on the number of nodes for the self-attention computation. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constructed by our proposed Hop2Token module. For each node, Hop2Token aggregates the neighborhood features from different hops into different representations and thereby produces a sequence of token vectors as one input. In this way, NAGphormer could be trained in a mini-batch manner and thus could scale to large graphs. Moreover, we mathematically show that as compared to a category of advanced Graph Neural Networks (GNNs), the decoupled Graph Convolutional Network, NAGphormer could learn more informative node representations from the multi-hop neighborhoods. Extensive experiments on benchmark datasets from small to large are conducted to demonstrate that NAGphormer consistently outperforms existing graph Transformers and mainstream GNNs. Code is available at https://github.com/JHL-HUST/NAGphormer.

Jinsong Chen, Kaiyuan Gao, Gaichao Li, Kun He• 2022

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy82.12
885
Node ClassificationPubmed
Accuracy89.7
742
Node ClassificationPubmed
Accuracy80.14
307
Node ClassificationCiteseer
Accuracy71.47
275
Node ClassificationwikiCS
Accuracy77.92
198
Node ClassificationOgbn-arxiv
Accuracy69.6
191
Node ClassificationPhoto
Mean Accuracy95.49
165
Node ClassificationAmazon Photo
Accuracy96.14
150
Node ClassificationPhysics
Accuracy97.34
145
Node ClassificationComputers
Mean Accuracy91.22
143
Showing 10 of 79 rows
...

Other info

Follow for update