On Proximity and Structural Role-based Embeddings in Networks

Author:

Rossi Ryan A.1,Jin Di2,Kim Sungchul1,Ahmed Nesreen K.3,Koutra Danai2,Lee John Boaz4

Affiliation:

1. Adobe Research, San Jose, CA

2. University of Michigan, MI

3. Intel Labs, Santa Clara, CA

4. Worcester Polytechnic Institute, Worcester, MA

Abstract

Structural roles define sets of structurally similar nodes that are more similar to nodes inside the set than outside, whereas communities define sets of nodes with more connections inside the set than outside. Roles based on structural similarity and communities based on proximity are fundamentally different but important complementary notions. Recently, the notion of structural roles has become increasingly important and has gained a lot of attention due to the proliferation of work on learning representations (node/edge embeddings) from graphs that preserve the notion of roles. Unfortunately, recent work has sometimes confused the notion of structural roles and communities (based on proximity) leading to misleading or incorrect claims about the capabilities of network embedding methods. As such, this article seeks to clarify the misconceptions and key differences between structural roles and communities, and formalize the general mechanisms (e.g., random walks and feature diffusion) that give rise to community- or role-based structural embeddings. We theoretically prove that embedding methods based on these mechanisms result in either community- or role-based structural embeddings. These mechanisms are typically easy to identify and can help researchers quickly determine whether a method preserves community- or role-based embeddings. Furthermore, they also serve as a basis for developing new and improved methods for community- or role-based structural embeddings. Finally, we analyze and discuss applications and data characteristics where community- or role-based embeddings are most appropriate.

Funder

Adobe Digital Experience faculty research award

Amazon faculty award

Google faculty award

National Science Foundation

Army Young Investigator

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science

Cited by 53 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. Social user role value analysis and trusted user autonomous diffusion for participatory crowdsensing;Computer Networks;2024-10

2. Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Leman Go Indifferent;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24

3. Representation Learning of Temporal Graphs with Structural Roles;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24

4. PaCEr: Network Embedding From Positional to Structural;Proceedings of the ACM Web Conference 2024;2024-05-13

5. DP-GCN: Node Classification by Connectivity and Local Topology Structure on Real-World Network;ACM Transactions on Knowledge Discovery from Data;2024-04-12

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