paper-with-me

홈 › Papers

RankNAS: Efficient Neural Architecture Search by Pairwise Ranking

2021-09-15 · EMNLP 2021 11 · Chi Hu, Chenglong Wang, Xiangnan Ma, Xia Meng, Yinqiao Li, Tong Xiao, Jingbo Zhu, Changliang Li

This paper addresses the efficiency challenge of Neural Architecture Search (NAS) by formulating the task as a ranking problem. Previous methods require numerous training examples to estimate the accurate performance of architectures, although the actual goal is to find the distinction between "good" and "bad" candidates. Here we do not resort to performance predictors. Instead, we propose a performance ranking method (RankNAS) via pairwise ranking. It enables efficient architecture search using much fewer training examples. Moreover, we develop an architecture selection method to prune the search space and concentrate on more promising candidates. Extensive experiments on machine translation and language modeling tasks show that RankNAS can design high-performance architectures while being orders of magnitude faster than state-of-the-art NAS systems.

📄 PDF Abstract BibTeX arXiv:2109.07383

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMachine TranslationNeural Architecture SearchTranslation

Similar Papers 제목 키워드 기반

An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking

2023-02-08 · Xubo Qin, Xiyuan Liu, Xiongfeng Zheng, Jie Liu 외

Although BERT-based ranking models have been commonly used in commercial search engines, they are usually time-consuming for online ranking tasks. Knowledge distillation, which aims at learning a smaller model with compa…

Document RankingKnowledge Distillation

Ranking architectures using meta-learning

2019-11-26 · Alina Dubatovka, Efi Kokiopoulou, Luciano Sbaiz, Andrea Gesmundo 외

Neural architecture search has recently attracted lots of research efforts as it promises to automate the manual design of neural networks. However, it requires a large amount of computing resources and in order to allev…

Meta-LearningNeural Architecture Search

Both Efficiency and Effectiveness! A Large Scale Pre-ranking Framework in Search System

2023-04-05 · Qihang Zhao, Rui-Jie Zhu, Liu Yang, He Yongming 외

In the realm of search systems, multi-stage cascade architecture is a prevalent method, typically consisting of sequential modules such as matching, pre-ranking, and ranking. It is generally acknowledged that the model u…

feature selection

From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search

2021-03-24 · Rui Li, Yunjiang Jiang, WenYun Yang, Guoyu Tang 외

We introduce deep learning models to the two most important stages in product search at JD.com, one of the largest e-commerce platforms in the world. Specifically, we outline the design of a deep learning system that ret…

Deep LearningRe-RankingRetrievalSemantic Retrieval

Ranking Passages for Argument Convincingness

2019-08-01 · WS 2019 8 · Peter Potash, Adam Ferguson, Timothy J. Hazen

In data ranking applications, pairwise annotation is often more consistent than cardinal annotation for learning ranking models. We examine this in a case study on ranking text passages for argument convincingness. Our t…