A Max-Flow Based Approach for Neural Architecture Search.

Neural Architecture Search (NAS) aims to automatically produce network architectures suitable to specific tasks on given datasets. Unlike previous NAS strategies based on reinforcement learning, genetic algorithm, Bayesian optimization, and differential programming, we formulate the NAS task as a Max-Flow problem on search space consisting of Directed Acyclic Graph (DAG) and thus propose a novel NAS approach, called MF-NAS, which defines the search space and designs the search strategy in a fully graphic manner. In MF-NAS, parallel edges with capacities are induced by combining different operations, including skip connection, convolutions and pooling, and the weights and capacities of the parallel edges are updated iteratively during the search process. Moreover, we interpret MF-NAS from the perspective of non-parametric density estimation and show the relationship between the flow of a graph and the corresponding classification accuracy of a neural network architecture. We evaluate the competitive efficacy of our proposed MF-NAS across different datasets with different search spaces that are used in DARTS/ENAS and NAS-Bench-201.