paper-with-me

홈 › Papers

NAS-Bench-101: Towards Reproducible Neural Architecture Search

2019-02-25 · Chris Ying, Aaron Klein, Esteban Real, Eric Christiansen, Kevin Murphy, Frank Hutter

Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the pre-computed dataset. We demonstrate its utility by analyzing the dataset as a whole and by benchmarking a range of architecture optimization algorithms.

📄 PDF Abstract BibTeX arXiv:1902.09635

Code (4)

automl/nas_benchmarks 공식 구현
google-research/nasbench 공식 구현 tf
DaveKim3872/nasbench-hpc tf
eric-vader/HD-BO-Additive-Models

Tasks

BenchmarkingNeural Architecture Search

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search

2022-06-18 · Yijian Qin, Ziwei Zhang, Xin Wang, Zeyang Zhang 외

Graph neural architecture search (GraphNAS) has recently aroused considerable attention in both academia and industry. However, two key challenges seriously hinder the further research of GraphNAS. First, since there is …

BenchmarkingGraph Neural NetworkNeural Architecture Search

Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement

2020-06-15 · Do-Guk Kim, Heung-Chang Lee

Recently, Neural Architecture Search (NAS) methods are introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to improve the given neural archit…

Neural Architecture Search

NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition

2021-01-01 · ICLR 2021 1 · Abhinav Mehrotra, Alberto Gil C. P. Ramos, Sourav Bhattacharya, Łukasz Dudziak 외

Powered by innovations in novel architecture design, noise tolerance techniques and increasing model capacity, Automatic Speech Recognition (ASR) made giant strides in improving prediction accuracies over the past decade…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Neural Architecture Searchspeech-recognition+1

RAISE: RAG Design as an Architecture Search Problem

2026-05-28 · Zhen Chen, Yibing Liu, Weihao Xie, Yu Liang 외 arxiv

Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context compression. In practice, these choices are often configured through…

Hyperparameter Optimization

Efficient Adaptive Transformer: An Empirical Study and Reproducible Framework

2025-10-14 · Jan Miller arxiv

The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for inpu…