SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.01899 · 2020

A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 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
walkerning/aw_nas canonical 2 of 2
FunctionStatusWhere it lives
sparse_mx_to_torch_sparse_tensor Ran walkerning/aw_nas/aw_nas/evaluator/arch_network.py
code served (permissive licence) · get_code("c97b99c4e8201a97")
valid_epoch Ran walkerning/aw_nas/aw_nas/controller/predictor_based.py
code served (permissive licence) · get_code("255cc6b99e2864f5")

Repositories linked to this paper

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

Abstract

This work proposes a novel Graph-based neural ArchiTecture Encoding Scheme, a.k.a. GATES, to improve the predictor-based neural architecture search. Specifically, different from existing graph-based schemes, GATES models the operations as the transformation of the propagating information, which mimics the actual data processing of neural architecture. GATES is a more reasonable modeling of the neural architectures, and can encode architectures from both the "operation on node" and "operation on edge" cell search spaces consistently. Experimental results on various search spaces confirm GATES's effectiveness in improving the performance predictor. Furthermore, equipped with the improved performance predictor, the sample efficiency of the predictor-based neural architecture search (NAS) flow is boosted. Codes are available at https://github.com/walkerning/aw_nas.

For agents

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

get_harvested_code_for_paper("2004.01899")
get_code_for_paper("2004.01899")
have("2004.01899")

Connect an agent — have() is free.