We propose a general and scalable global optimization framework directly operating on annotated graph data by introducing a Bayesian graph neural network to approximate the expensive-to-evaluate objectives. It prevents the cubical complexity of Gaussian processes and can scale linearly with the number of observations. Its parallelized variant makes it scalable. We provide strict theoretical support on its convergence. Intensive experiments conducted on both artificial and real-world problems, including molecular discovery and urban road network design, demonstrate the effectiveness of the proposed methods compared with the current state of the art.
|Journal||IEEE Transactions on Neural Networks and Learning Systems|
|Publication status||Accepted/In press - 2020|
Scopus Subject Areas
- Computer Science Applications
- Computer Networks and Communications
- Artificial Intelligence
- Attributed graphs
- Bayesian optimization
- graph neural networks (GNNs)
- structure optimization.