# GraphNAS: Graph Neural Architecture Search with Reinforcement Learning

arXiv: https://arxiv.org/abs/1904.09981 · HTML: https://mlsanity.com/paper/1904.09981/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 30 of 41)

- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Recent Advances of Multimodal Continual Learning: A Comprehensive Survey](https://mlsanity.com/paper/2410.05352/) (2024)
- [Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks](https://mlsanity.com/paper/2104.07886/) (2021)
- [Pooling Architecture Search for Graph Classification](https://mlsanity.com/paper/2108.10587/) (2021)
- [Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets](https://mlsanity.com/paper/2103.00794/) (2021)
- [Learning How to Propagate Messages in Graph Neural Networks](https://mlsanity.com/paper/2310.00697/) (2023)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective](https://mlsanity.com/paper/2112.14531/) (2021)
- [Continual Graph Learning: A Survey](https://mlsanity.com/paper/2301.12230/) (2023)
- [G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency](https://mlsanity.com/paper/2109.08983/) (2021)
- [GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design](https://mlsanity.com/paper/2112.11594/) (2021)
- [MAG-GNN: Reinforcement Learning Boosted Graph Neural Network](https://mlsanity.com/paper/2310.19142/) (2023)
- [Dynamic Layer Tying for Parameter-Efficient Transformers](https://mlsanity.com/paper/2401.12819/) (2024)
- [Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2202.09177/) (2022)
- [AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks](https://mlsanity.com/paper/2303.07669/) (2023)
- [AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2301.03049/) (2023)
- [Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification](https://mlsanity.com/paper/2302.08671/) (2023)
- [A Versatile Graph Learning Approach through LLM-based Agent](https://mlsanity.com/paper/2309.04565/) (2023)
- [Calibrated Dataset Condensation for Faster Hyperparameter Search](https://mlsanity.com/paper/2405.17535/) (2024)
- [Combinatorial Optimization with Automated Graph Neural Networks](https://mlsanity.com/paper/2406.02872/) (2024)
- [Survey of Graph Neural Network for Internet of Things and NextG Networks](https://mlsanity.com/paper/2405.17309/) (2024)
- [Learn Layer-wise Connections in Graph Neural Networks](https://mlsanity.com/paper/2112.13585/) (2021)
- [Graph Property Prediction on Open Graph Benchmark: A Winning Solution by Graph Neural Architecture Search](https://mlsanity.com/paper/2207.06027/) (2022)
- [Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach](https://mlsanity.com/paper/2211.10990/) (2022)
- [Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification](https://mlsanity.com/paper/2406.16357/) (2024)
- [Relatron: Automating Relational Machine Learning over Relational Databases](https://mlsanity.com/paper/2602.22552/) (2026)
- [Bilevel Optimization for Neural Architecture Search](https://mlsanity.com/paper/2606.29582/) (2026)
- [Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models](https://mlsanity.com/paper/2408.06717/) (2024)
- [Agentic Neural Architecture Search](https://mlsanity.com/paper/2607.07984/) (2026)
- [Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning](https://mlsanity.com/paper/2106.05221/) (2021)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and then trains the recurrent network with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation data set. Extensive experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that GraphNAS can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network. On node classification tasks, GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy.