Cost-aware Graph Generation: A Deep Bayesian Optimization Approach
Keywords:Graph-based Machine Learning, Sampling/Simulation-based Search, Sequential Decision Making, Online Learning & Bandits
AbstractGraph-structured data is ubiquitous throughout the natural and social sciences, ranging from complex drug molecules to artificial neural networks. Evaluating their functional properties, e.g., drug effectiveness and prediction accuracy, is usually costly in terms of time, money, energy, or environment, becoming a bottleneck for the graph generation task. In this work, from the perspective of saving cost, we propose a novel Cost-Aware Graph Generation (CAGG) framework to generate graphs with optimal properties at as low cost as possible. By introducing a robust Bayesian graph neural network as the surrogate model and a goal-oriented training scheme for the generation model, the CAGG can approach the real expensive evaluation function and generate search space close to the optimal property, to avoid unnecessary evaluations. Intensive experiments conducted on two challenging real-world applications, including molecular discovery and neural architecture search, demonstrate its effectiveness and applicability. The results show that it can generate the optimal graphs and reduce the evaluation costs significantly compared to the state-of-the-art.
How to Cite
Cui, J., Yang, B., Sun, B., & Liu, J. (2021). Cost-aware Graph Generation: A Deep Bayesian Optimization Approach. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 7142-7150. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16878
AAAI Technical Track on Machine Learning I