# Probabilistic Dual Network Architecture Search on Graphs

arXiv: https://arxiv.org/abs/2003.09676 · HTML: https://mlsanity.com/paper/2003.09676/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2020.

## Built on by (most cited first, 15 of 15)

- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Automated Machine Learning on Graphs: A Survey](https://mlsanity.com/paper/2103.00742/) (2021)
- [On Representation Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2111.04964/) (2021)
- [Architectural Backdoors in Neural Networks](https://mlsanity.com/paper/2206.07840/) (2022)
- [NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search](https://mlsanity.com/paper/2206.09166/) (2022)
- [Do We Need Anisotropic Graph Neural Networks?](https://mlsanity.com/paper/2104.01481/) (2021)
- [Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification](https://mlsanity.com/paper/2108.06317/) (2021)
- [Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions](https://mlsanity.com/paper/2201.01288/) (2022)
- [Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks](https://mlsanity.com/paper/2305.14065/) (2023)
- [Knowledge-aware Evolutionary Graph Neural Architecture Search](https://mlsanity.com/paper/2411.17339/) (2024)
- [Rapid Model Architecture Adaption for Meta-Learning](https://mlsanity.com/paper/2109.04925/) (2021)
- [Model Architecture Adaption for Bayesian Neural Networks](https://mlsanity.com/paper/2202.04392/) (2022)
- [Efficient Automatic Machine Learning via Design Graphs](https://mlsanity.com/paper/2210.12257/) (2022)
- [Automated Polynomial Filter Learning for Graph Neural Networks](https://mlsanity.com/paper/2307.07956/) (2023)
- [NodeNAS: Node-Specific Graph Neural Architecture Search for Out-of-Distribution Generalization](https://mlsanity.com/paper/2503.02448/) (2025)

## Abstract (arXiv)

We present the first differentiable Network Architecture Search (NAS) for Graph Neural Networks (GNNs). GNNs show promising performance on a wide range of tasks, but require a large amount of architecture engineering. First, graphs are inherently a non-Euclidean and sophisticated data structure, leading to poor adaptivity of GNN architectures across different datasets. Second, a typical graph block contains numerous different components, such as aggregation and attention, generating a large combinatorial search space. To counter these problems, we propose a Probabilistic Dual Network Architecture Search (PDNAS) framework for GNNs. PDNAS not only optimises the operations within a single graph block (micro-architecture), but also considers how these blocks should be connected to each other (macro-architecture). The dual architecture (micro- and marco-architectures) optimisation allows PDNAS to find deeper GNNs on diverse datasets with better performance compared to other graph NAS methods. Moreover, we use a fully gradient-based search approach to update architectural parameters, making it the first differentiable graph NAS method. PDNAS outperforms existing hand-designed GNNs and NAS results, for example, on the PPI dataset, PDNAS beats its best competitors by 1.67 and 0.17 in F1 scores.