paper-with-me

홈 › Papers

Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering

2022-04-29 · Thorir Mar Ingolfsson, Mark Vero, Xiaying Wang, Lorenzo Lamberti, Luca Benini, Matteo Spallanzani

The computational demands of neural architecture search (NAS) algorithms are usually directly proportional to the size of their target search spaces. Thus, limiting the search to high-quality subsets can greatly reduce the computational load of NAS algorithms. In this paper, we present Clustering-Based REDuction (C-BRED), a new technique to reduce the size of NAS search spaces. C-BRED reduces a NAS space by clustering the computational graphs associated with its architectures and selecting the most promising cluster using proxy statistics correlated with network accuracy. When considering the NAS-Bench-201 (NB201) data set and the CIFAR-100 task, C-BRED selects a subset with 70% average accuracy instead of the whole space's 64% average accuracy.

📄 PDF Abstract BibTeX arXiv:2204.14103

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringGraph ClusteringNeural Architecture Search

Similar Papers 제목 키워드 기반

Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights

2025-01-01 · CVPR 2025 1 · Ondrej Tybl, Lukas Neumann

Deep learning has revolutionized computer vision, but it achieved its tremendous success using deep network architectures which are mostly hand-crafted and therefore likely suboptimal. Neural Architecture Search (NAS…

image-classificationImage ClassificationNeural Architecture Search

Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights

2025-02-07 · Ondřej Týbl, Lukáš Neumann

Deep learning has revolutionized computer vision, but it achieved its tremendous success using deep network architectures which are mostly hand-crafted and therefore likely suboptimal. Neural Architecture Search (NAS) ai…

image-classificationImage ClassificationNeural Architecture Search

Transferrable Surrogates in Expressive Neural Architecture Search Spaces

2025-04-17 · Shiwen Qin, Gabriela Kadlecová, Martin Pilát, Shay B. Cohen 외

Neural architecture search (NAS) faces a challenge in balancing the exploration of expressive, broad search spaces that enable architectural innovation with the need for efficient evaluation of architectures to effective…

Neural Architecture Search

Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars

2022-11-03 · NeurIPS 2023 11 · Simon Schrodi, Danny Stoll, Binxin Ru, Rhea Sukthanker 외

The discovery of neural architectures from simple building blocks is a long-standing goal of Neural Architecture Search (NAS). Hierarchical search spaces are a promising step towards this goal but lack a unifying search …

AutoMLBayesian OptimizationNeural Architecture Search

Evolutionary Neural Architecture Search for 3D Point Cloud Analysis

2024-08-10 · Yisheng Yang, Guodong Du, Chean Khim Toa, Ho-Kin Tang 외

Neural architecture search (NAS) automates neural network design by using optimization algorithms to navigate architecture spaces, reducing the burden of manual architecture design. While NAS has achieved success, applyi…

Evolutionary AlgorithmsNavigateNeural Architecture Search