# Auto-GNN: Neural Architecture Search of Graph Neural Networks

arXiv: https://arxiv.org/abs/1909.03184 · HTML: https://mlsanity.com/paper/1909.03184/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2019.

## Built on by (most cited first, 30 of 74)

- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Dirichlet Energy Constrained Learning for Deep Graph Neural Networks](https://mlsanity.com/paper/2107.02392/) (2021)
- [Search to aggregate neighborhood for graph neural network](https://mlsanity.com/paper/2104.06608/) (2021)
- [Automated Machine Learning on Graphs: A Survey](https://mlsanity.com/paper/2103.00742/) (2021)
- [PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm](https://mlsanity.com/paper/2203.00638/) (2022)
- [Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study](https://mlsanity.com/paper/2108.10521/) (2021)
- [Pooling Architecture Search for Graph Classification](https://mlsanity.com/paper/2108.10587/) (2021)
- [Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications](https://mlsanity.com/paper/2206.07922/) (2022)
- [Rethinking Graph Neural Architecture Search from Message-passing](https://mlsanity.com/paper/2103.14282/) (2021)
- [AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs](https://mlsanity.com/paper/2304.09595/) (2023)
- [NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search](https://mlsanity.com/paper/2206.09166/) (2022)
- [Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching](https://mlsanity.com/paper/2312.16560/) (2023)
- [Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs](https://mlsanity.com/paper/2302.12357/) (2023)
- [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)
- [Graph Decision Transformer](https://mlsanity.com/paper/2303.03747/) (2023)
- [Orthogonal Graph Neural Networks](https://mlsanity.com/paper/2109.11338/) (2021)
- [Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective](https://mlsanity.com/paper/2112.14531/) (2021)
- [AutoGEL: An Automated Graph Neural Network with Explicit Link Information](https://mlsanity.com/paper/2112.01064/) (2021)
- [RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search](https://mlsanity.com/paper/2206.06757/) (2022)
- [AutoGL: A Library for Automated Graph Learning](https://mlsanity.com/paper/2104.04987/) (2021)
- [G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency](https://mlsanity.com/paper/2109.08983/) (2021)
- [MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data](https://mlsanity.com/paper/2310.02275/) (2023)
- [Adaptive Label Smoothing To Regularize Large-Scale Graph Training](https://mlsanity.com/paper/2108.13555/) (2021)
- [Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions](https://mlsanity.com/paper/2201.01288/) (2022)
- [MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment](https://mlsanity.com/paper/2307.08065/) (2023)
- [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)
- [Adversarially Robust Neural Architecture Search for Graph Neural Networks](https://mlsanity.com/paper/2304.04168/) (2023)

## Abstract (arXiv)

Graph neural networks (GNN) has been successfully applied to operate on the graph-structured data. Given a specific scenario, rich human expertise and tremendous laborious trials are usually required to identify a suitable GNN architecture. It is because the performance of a GNN architecture is significantly affected by the choice of graph convolution components, such as aggregate function and hidden dimension. Neural architecture search (NAS) has shown its potential in discovering effective deep architectures for learning tasks in image and language modeling. However, existing NAS algorithms cannot be directly applied to the GNN search problem. First, the search space of GNN is different from the ones in existing NAS work. Second, the representation learning capacity of GNN architecture changes obviously with slight architecture modifications. It affects the search efficiency of traditional search methods. Third, widely used techniques in NAS such as parameter sharing might become unstable in GNN. To bridge the gap, we propose the automated graph neural networks (AGNN) framework, which aims to find an optimal GNN architecture within a predefined search space. A reinforcement learning based controller is designed to greedily validate architectures via small steps. AGNN has a novel parameter sharing strategy that enables homogeneous architectures to share parameters, based on a carefully-designed homogeneity definition. Experiments on real-world benchmark datasets demonstrate that the GNN architecture identified by AGNN achieves the best performance, comparing with existing handcrafted models and tradistional search methods.