A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
This work addresses the need for more efficient neural architecture search methods, particularly for researchers and practitioners in automated machine learning, though it is incremental as it builds on existing graph-based encoding approaches.
The authors tackled the problem of improving predictor-based neural architecture search by proposing GATES, a graph-based encoding scheme that models operations as information transformations, which enhanced predictor performance and boosted sample efficiency in NAS flows.
This work proposes a novel Graph-based neural ArchiTecture Encoding Scheme, a.k.a. GATES, to improve the predictor-based neural architecture search. Specifically, different from existing graph-based schemes, GATES models the operations as the transformation of the propagating information, which mimics the actual data processing of neural architecture. GATES is a more reasonable modeling of the neural architectures, and can encode architectures from both the "operation on node" and "operation on edge" cell search spaces consistently. Experimental results on various search spaces confirm GATES's effectiveness in improving the performance predictor. Furthermore, equipped with the improved performance predictor, the sample efficiency of the predictor-based neural architecture search (NAS) flow is boosted. Codes are available at https://github.com/walkerning/aw_nas.