paper-conference

Leverage the beneficial knowledge implicit in low-fidelity information (e.g., one/zero-shot estimation) to mitigate the “cold-start” problem of predictor-based NAS.

This work proposes a new encoding scheme for neural architectures, the Training-Analogous Graph-based ArchiTecture Encoding Scheme (TA-GATES). TA-GATES encodes an NN architecture in a way that is analogous to its training.