Probabilistic Dual Network Architecture Search on Graphs

by   Yiren Zhao, et al.

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.


page 1

page 2

page 3

page 4


Learned Low Precision Graph Neural Networks

Deep Graph Neural Networks (GNNs) show promising performance on a range ...

Efficient and Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search

Graph neural networks (GNNs) are powerful tools for performing data scie...

Adversarially Robust Neural Architecture Search for Graph Neural Networks

Graph Neural Networks (GNNs) obtain tremendous success in modeling relat...

Pooling Architecture Search for Graph Classification

Graph classification is an important problem with applications across ma...

Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs

Graph neural architecture search (NAS) has gained popularity in automati...

GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models

Neural architectures can be naturally viewed as computational graphs. Mo...

A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction

In computer vision research, the process of automating architecture engi...

Please sign up or login with your details

Forgot password? Click here to reset