Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search (Full version)
Not on the map. Why?
Abstract (arXiv)
The number of graph neural network (GNN) architectures has increased rapidly due to the growing adoption of graph analysis. Although we use GNNs in wide application scenarios, it is a laborious task to design/select optimal GNN architectures in diverse graphs. To reduce human efforts, graph neural architecture search (Graph NAS) has been used to search for a sub-optimal GNN architecture that combines existing components. However, existing Graph NAS methods lack explainability to understand the reasons why the model architecture is selected because they use complex search space and neural models to select architecture. Therefore, we propose an explainable Graph NAS method, called ExGNAS, which consists of (i) a simple search space that can adapt to various graphs and (ii) a search algorithm with Monte-Carlo tree that makes the decision process explainable. The combination of our search space and algorithm achieves finding accurate GNN models and the important functions within the search space. We comprehensively evaluate ExGNAS compared with four state-of-the-art Graph NAS methods in twelve graphs. Our experimental results show that ExGNAS achieves high average accuracy and efficiency; improving accuracy up to 26.1% and reducing run time up to 88%. Furthermore, we show the effectiveness of explainability by questionnaire-based user study and architecture analysis.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 30 Aug 2023.
Builds on
27 of 46 references.
References · 27
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
- 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
- 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
- 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
- 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
- 2019Random Search and Reproducibility for Neural Architecture Searchcited by 253
- 2020Design Space for Graph Neural Networkscited by 182
- 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
15 more
- 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
- 2020AutoML-Zero: Evolving Machine Learning Algorithms From Scratchcited by 137
- 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
- 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
- 2020Simplifying Architecture Search for Graph Neural Networkcited by 27
- 2022NAS-Bench-Graph: Benchmarking Graph Neural Architecture Searchcited by 25
- 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
- 2023Auto-HeG: Automated Graph Neural Network on Heterophilic Graphscited by 23
- 2020AutoGraph: Automated Graph Neural Networkcited by 21
- 2022A Survey on Fairness for Machine Learning on Graphscited by 20
- 2018Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Searchcited by 17
- 2021FOX-NAS: Fast, On-device and Explainable Neural Architecture Searchcited by 7
- 2021Learning Interpretable Models Through Multi-Objective Neural Architecture Searchcited by 5
- 2023Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networkscited by 5
- 2023A Simple and Scalable Graph Neural Network for Large Directed Graphscited by 1
Built on by
Not cited yet.