NAS-Bench-102: Extending the Scope of Reproducible Neural Architecture Search

By Xuanyi Dong, Yi Yang. 2020

46 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Comprehensive Survey of Neural Architecture Search (2020, background): “, some work is also devoted to providing a unified evaluation platform for popular NAS methods [78, 126].”
Single Path One-Shot Neural Architecture Search with Uniform Sampling (2019, methodology): “Correlation analysis requires to achieve the performances of a large number of architectures, but training lots of architectures from scratch is very timeconsuming, which also requires a large number of GPU resources, so we use the NAS-Bench-201 [7] to analyze our method.”
AMER: Automatic Behavior Modeling and Interaction Exploration in Recommender System (2020, unknown): “Though diverse complex searching algorithms [5, 7, 10, 13] have been coupled with one-shot NAS, recent studies [4, 14, 37] reveal that the primitive random search with one-shot strategy is a surprisingly competitive baseline compared to gradient-based methods such as DARTS [44] and SNAS [76] or RL-b”
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (2021, methodology): “As shown in Figure 10, in NAS-Bench201 the training accuracy strongly correlates with test accuracy.”
Supplementary material for DEHB: Evolutionary Hyperband for Scalable, Robust and Efﬁcient Hyperparameter Optimization (2021, methodology): “To alleviate issues of direct applicability of weight sharing algorithms to NAS-Bench-101, [Dong and Yang, 2020] proposed NAS-Bench-201.”
NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search (2020, methodology): “Despite the great advancements of these methods, the exact results of many NAS papers are often hard to reproduce (Li & Talwalkar, 2019; Yu et al., 2020; Yang et al., 2020).”
NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search (2020, methodology): “NAS-Bench-201 (Dong & Yang, 2020), in contrast, uses a search space with a ﬁxed number of nodes and edges, hence allowing for a straight-forward application of one-shot NAS methods.”