Unchain the Search Space with Hierarchical Differentiable Architecture Search

Authors: Guanting Liu, Yujie Zhong, Sheng Guo, Matthew R. Scott, Weilin Huang8644-8652

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on CIFAR10 and Image Net demonstrate the effectiveness of the proposed HDAS.
Researcher Affiliation Industry Malong LLC {gualiu, jaszhong, sheng, mscott, whuang}@malongtech.com
Pseudocode No No pseudocode or algorithm blocks were found in the paper.
Open Source Code Yes Code is available at: https://github.com/msight-tech/research-HDAS
Open Datasets Yes We conduct experiments on CIFAR10 and Image Net.
Dataset Splits Yes In the search of cell-level structure, we follow DARTS (Liu, Simonyan, and Yang 2018) by using the same search space, hyperparameters and training scheme. [...] For training a single model, we use the same strategy and data processing methods as DARTS. More details can be found in SM.
Hardware Specification No No explicit mention of specific GPU/CPU models, processors, or detailed computer specifications used for running experiments was found.
Software Dependencies No No specific software versions or library dependencies were explicitly mentioned for reproducibility.
Experiment Setup No The paper mentions following the hyperparameters and training scheme of DARTS, but does not explicitly provide the specific values or details within the paper itself.