SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.00195 · 2019

SGAS: Sequential Greedy Architecture Search

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
lightaime/sgas pwc_unofficial 2 of 7
FunctionStatusWhere it lives
adjust_lr Ran lightaime/sgas/cnn/train_imagenet.py
code served (permissive licence) · get_code("e7ef53e9c5847e3e")
load_data Ran lightaime/sgas/gcn/gcn_point/load_modelnet.py
code served (permissive licence) · get_code("a0f3e74b47090f07")
accuracy Not yet run lightaime/sgas/cnn/utils.py
code served (permissive licence) · get_code("469bf48752905889")
count_parameters_in_MB Not yet run lightaime/sgas/cnn/utils.py
code served (permissive licence) · get_code("3e816289579cc9e9")
drop_path Not yet run lightaime/sgas/cnn/utils.py
code served (permissive licence) · get_code("13c2719404e25b25")
drop_path Not yet run lightaime/sgas/gcn/gcn_graph/model.py
code served (permissive licence) · get_code("a8c6a004344526a2")
translate_pointcloud Not yet run lightaime/sgas/gcn/gcn_point/load_modelnet.py
code served (permissive licence) · get_code("791051c3e72b67d2")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Architecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, discovered architectures often fail to generalize in the final evaluation. Architectures with a higher validation accuracy during the search phase may perform worse in the evaluation. Aiming to alleviate this common issue, we introduce sequential greedy architecture search (SGAS), an efficient method for neural architecture search. By dividing the search procedure into sub-problems, SGAS chooses and prunes candidate operations in a greedy fashion. We apply SGAS to search architectures for Convolutional Neural Networks (CNN) and Graph Convolutional Networks (GCN). Extensive experiments show that SGAS is able to find state-of-the-art architectures for tasks such as image classification, point cloud classification and node classification in protein-protein interaction graphs with minimal computational cost. Please visit https://www.deepgcns.org/auto/sgas for more information about SGAS.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1912.00195")
get_code_for_paper("1912.00195")
have("1912.00195")

Connect an agent — have() is free.