DFG-NAS: Deep and Flexible Graph Neural Architecture Search Article Swipe

MAKE IMPACT

Wentao Zhang , Zheyu Lin , Yu Shen , Yang Li , Zhi Yang , Bin Cui · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2206.08582

Graph neural networks (GNNs) have been intensively applied to various graph-based applications. Despite their success, manually designing the well-behaved GNNs requires immense human expertise. And thus it is inefficient to discover the potentially optimal data-specific GNN architecture. This paper proposes DFG-NAS, a new neural architecture search (NAS) method that enables the automatic search of very deep and flexible GNN architectures. Unlike most existing methods that focus on micro-architectures, DFG-NAS highlights another level of design: the search for macro-architectures on how atomic propagation (\textbf{\texttt{P}}) and transformation (\textbf{\texttt{T}}) operations are integrated and organized into a GNN. To this end, DFG-NAS proposes a novel search space for \textbf{\texttt{P-T}} permutations and combinations based on message-passing dis-aggregation, defines four custom-designed macro-architecture mutations, and employs the evolutionary algorithm to conduct an efficient and effective search. Empirical studies on four node classification tasks demonstrate that DFG-NAS outperforms state-of-the-art manual designs and NAS methods of GNNs.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2206.08582

PDF

https://arxiv.org/pdf/2206.08582

OA Status

green

Cited By

3

Related Works

10

OpenAlex ID

https://openalex.org/W4283216946

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4283216946

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2206.08582

Digital Object Identifier

Title

DFG-NAS: Deep and Flexible Graph Neural Architecture Search

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-06-17

Full publication date if available

Authors

Wentao Zhang, Zheyu Lin, Yu Shen, Yang Li, Zhi Yang, Bin Cui

List of authors in order

Landing page

https://arxiv.org/abs/2206.08582

Publisher landing page

PDF URL

https://arxiv.org/pdf/2206.08582

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2206.08582

Direct OA link when available

Concepts

Computer science, Architecture, Graph, Macro, Focus (optics), Theoretical computer science, Artificial neural network, Evolutionary algorithm, Node (physics), Search algorithm, Artificial intelligence, Algorithm, Engineering, Programming language, Visual arts, Physics, Art, Optics, Structural engineering

Top concepts (fields/topics) attached by OpenAlex

Cited by

3

Total citation count in OpenAlex

Citations by year (recent)

2025: 1, 2023: 2

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload