ml

Meta-learning without data via Wasserstein distributionally-robust model fusion
Existing meta-learning works assume that each task has available training and testing data. However, there are many available …
Zhenyi Wang, Xiaoyang Wang, Li Shen, Qiuling Suo, Kaiqiang Song, Dong Yu, Yan Shen, Mingchen Gao
PDF Cite
CATE: Computation-aware Neural Architecture Encoding with Transformers
Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search …
Shen Yan, Kaiqiang Song, Fei Liu, Mi Zhang
PDF Cite Code Slides Video