• DOI:10.1609/AAAI.V34I04.5764
Corpus ID: 53776372

InstaNAS: Instance-aware Neural Architecture Search

@inproceedings{Cheng2020InstaNASIN,
  title={InstaNAS: Instance-aware Neural Architecture Search},
  author={A. Cheng and Chieh Hubert Lin and Da-Cheng Juan and W. Wei and Min Sun},
  booktitle={AAAI},
  year={2020}
}

A. Cheng, Chieh Hubert Lin, +2 authors Min Sun

Published in AAAI 2020

Computer Science, Mathematics

Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuitively, electing domain-expert architectures that are proficient in domain-specific features can further benefit architecture related objectives such as latency. In this paper, we… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed