Automatic Graph Topology-Aware Transformer

TL;DR

This paper introduces EGTAS, an automated framework for designing effective graph Transformer architectures through evolutionary search, reducing manual effort and achieving competitive performance across various graph tasks.

Contribution

It presents a comprehensive search space and a surrogate performance prediction model for automated graph Transformer architecture search.

Findings

EGTAS constructs high-performance graph Transformers.

Automated search rivals manual and baseline methods.

Effective across diverse graph datasets and tasks.

Abstract

Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model's representation capabilities. However, manually determining the suitable Transformer architecture for a specific graph dataset or task requires extensive expert knowledge and laborious trials. This paper proposes an evolutionary graph Transformer architecture search framework (EGTAS) to automate the construction of strong graph Transformers. We build a comprehensive graph Transformer search space with the micro-level and macro-level designs. EGTAS evolves graph Transformer topologies at the macro level and graph-aware strategies at the micro level. Furthermore, a surrogate model based on generic architectural coding is proposed to directly predict the performance of graph Transformers, substantially reducing the evaluation cost of evolutionary search. We demonstrate the efficacy of EGTAS across a range of graph-level and node-level tasks, encompassing both small-scale and large-scale graph datasets. Experimental results and ablation studies show that EGTAS can construct high-performance architectures that rival state-of-the-art manual and automated baselines.