# Neural Architecture Search Over a Graph Search Space

Source: [Neural Architecture Search Over a Graph Search Space](<https://www.sota2.com/research/paper/68fa661f1e209131cea0e7c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:58:47.394Z

Authors: Stanis{\\l}aw Jastrz\\k{e}bski, Quentin de Laroussilhe, Mingxing Tan, Xiao Ma, Neil Houlsby, Andrea Gesmundo

Published: 2018-12-27T09:04:17.000Z

## Abstract

Neural Architecture Search (NAS) enabled the discovery of state-of-the-art architectures in many domains. However, the success of NAS depends on the definition of the search space. Current search spaces are defined as a static sequence of decisions and a set of available actions for each decision. Each possible sequence of actions defines an architecture. We propose a more expressive class of search space: directed graphs. In our formalism, each decision is a vertex and each action is an edge. This allows us to model iterative and branching architecture design decisions. We demonstrate in simulation, and on image classification experiments, basic iterative and branching search structures, and show that the graph representation improves sample efficiency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1812.10666>)

[PDF](<https://arxiv.org/pdf/1812.10666.pdf>)