Fitness landscape analysis of graph neural network architecture search spaces

Author:

Nunes Matheus1,Fraga Paulo M.1,Pappa Gisele L.1

Affiliation:

1. Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil

Funder

CNPq

FAPEMIG

H2020 European Institute of Innovation and Technology

MPMG

MCTIC/RNP

Publisher

ACM

Reference39 articles.

1. Search space boundaries in neural network error landscape analysis

2. Neural Architecture Search: A Survey;Elsken Thomas;Journal of Machine Learning Research (JMLR),2019

3. Graph Neural Architecture Search

4. Analysis of the Complexity of the Automatic Pipeline Generation Problem

5. William L. Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems (NeurIPS). 1024--1034. William L. Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems (NeurIPS). 1024--1034.

Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Universal Local Attractors on Graphs;Applied Sciences;2024-05-25

2. Channel Configuration for Neural Architecture: Insights from the Search Space;Proceedings of the Genetic and Evolutionary Computation Conference;2023-07-12

3. A data-driven approach to neural architecture search initialization;Annals of Mathematics and Artificial Intelligence;2023-03-22

4. Minimum-Fuel Low-Thrust Trajectory Optimization Via a Direct Adaptive Evolutionary Approach;IEEE Transactions on Aerospace and Electronic Systems;2023

5. Local Fitness Landscape Exploration Based Genetic Algorithms;IEEE Access;2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3