On the Expressive Power of Message-Passing Neural Networks as Global Feature Map Transformers

Author:

Geerts FlorisORCID,Steegmans JasperORCID,Van den Bussche JanORCID

Publisher

Springer International Publishing

Reference25 articles.

1. Abboud, R., Ceylan, I., Grohe, M., Lukasiewicz, T.: The surprising power of graph neural networks with random node initialization. In: Zhou, Z.H. (ed.) Proceedings 30th International Joint Conference on Artificial Intelligence, pp. 2112–2118. ijcai.org (2021)

2. Abiteboul, S., Hull, R., Vianu, V.: Foundations of Databases. Addison-Wesley, Boston (1995)

3. Arora, R., Basu, A., Mianjy, P., Mukherjee, A.: Understanding deep neural networks with rectified linear units. In: Proceedings 6th International Conference on Learning Representations. OpenReview.net (2018)

4. Azizian, W., Lelarge, M.: Expressive power of invariant and equivariant graph neural networks. In: Proceedings 9th International Conference on Learning Representations. OpenReview.net (2021)

5. Balcilar, M., Héroux, P., et al.: Breaking the limits of message passing graph neural networks. In: Meila, M., Zhang, T. (eds.) Proceedings 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 599–608 (2021)

Cited by 3 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. The Descriptive Complexity of Graph Neural Networks;2023 38th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS);2023-06-26

2. Learning Graph Neural Networks using Exact Compression;Proceedings of the 6th Joint Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA);2023-06-18

3. A Query Language Perspective on Graph Learning;Proceedings of the 42nd ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems;2023-06-18

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