Shengyao Lu, Keith Mills, Di Niu, Mohammad Salameh, Jiao He, Fred Han, Fengyu Sun, Chunhua Zhou
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Neural Architecture Search is a costly practice. The fact that a search space can span a vast number of design choices with each architecture evaluation taking nontrivial overhead makes it hard for an algorithm to sufficiently explore candidate networks. In this paper, we propose Auto-Build, a scheme which learns to align the latent embeddings of operations and architecture modules with the groundtruth performance of the architectures they appear in. By doing so, AutoBuild is capable of assigning interpretable importance scores to architecture modules, such as individual operation features and larger macro operation sequences such that high-performance neural networks can be constructed without any need for search. Through experiments performed on state-of-the-art image classification, segmentation, and Stable Diffusion models, we show that by mining a relatively small set of evaluated architectures, AutoBuild can learn to build high-quality architectures directly or help to reduce search space to focus on relevant areas, finding better architectures that outperform both the original labeled ones and ones found by search baselines.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.13293")
get_code_for_paper("2403.13293")
have("2403.13293")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.13293.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.13293)
Connect an agent — have() is free.