Global optimization of graph acquisition functions for neural architecture search
This work addresses a bottleneck in neural architecture search for researchers, though it is incremental as it builds on existing graph BO methods.
The paper tackles the challenge of optimizing acquisition functions in graph Bayesian optimization for neural architecture search by developing explicit formulations based on graph properties like reachability and shortest paths, and it demonstrates efficacy by efficiently finding optimal architectures in benchmarks.
Graph Bayesian optimization (BO) has shown potential as a powerful and data-efficient tool for neural architecture search (NAS). Most existing graph BO works focus on developing graph surrogates models, i.e., metrics of networks and/or different kernels to quantify the similarity between networks. However, the acquisition optimization, as a discrete optimization task over graph structures, is not well studied due to the complexity of formulating the graph search space and acquisition functions. This paper presents explicit optimization formulations for graph input space including properties such as reachability and shortest paths, which are used later to formulate graph kernels and the acquisition function. We theoretically prove that the proposed encoding is an equivalent representation of the graph space and provide restrictions for the NAS domain with either node or edge labels. Numerical results over several NAS benchmarks show that our method efficiently finds the optimal architecture for most cases, highlighting its efficacy.