.png){kind=icon}
.png){kind=icon}
Return
Automatic Graph Topology-Aware Transformer
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2024.3440269.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 article proposes an evolutionary graph Transformer architecture search (EGTAS) framework 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.
Keywords:
Transformers
Computer architecture
Topology
Computational modeling
Search problems
Encoding
Predictive models
Graph neural network (GNN)
graph Transformer
graph-aware strategy
neural architecture search
performance predictor
topology design
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W