On the modelling and impact of negative edges in graph convolutional networks for node classification

Research output: Contribution to conferencePaperpeer-review

168 Downloads (Pure)

Abstract

Signed graphs are important data structures to simultaneously express positive and negative relationships. Their application ranges from structural health monitoring to financial models, where the meaning and properties of negative relationships can play a significant role. In this paper, we provide a comprehensive examination of existing approaches for the integration of signed edges into the Graph Convolutional Network (GCN) framework for node classification. Here, we use a combination of theoretical and empirical analysis to gain a deeper understanding of the strengths and limitations of different mechanisms and to identify areas for possible improvement. We compare six different approaches to the integration of negative link information within the framework of the simple GCN. In particular, we analyze sensitivity towards feature noise, negative edge noise and positive edge noise, as well as robustness towards feature scaling and translation, explaining the results obtained on the basis of individual model assumptions and biases. Our findings highlight the importance of capturing the meaning of negative links in a given domain context, and appropriately reflecting it in the choice of GCN model. Our code is available at https://github.com/dinhtrang24/Signed-GCN.
Original languageEnglish
Pages1-21
Number of pages21
Publication statusAccepted/In press - 28 Oct 2023
EventNeurIPS 2023 Workshop: New Frontiers in Graph Learning - New Orleans Convention Center, Louisiana, United States, New Orleans, United States
Duration: 15 Dec 2023 → …
https://glfrontiers.github.io/

Conference

ConferenceNeurIPS 2023 Workshop: New Frontiers in Graph Learning
Country/TerritoryUnited States
CityNew Orleans
Period15/12/23 → …
Internet address

Fingerprint

Dive into the research topics of 'On the modelling and impact of negative edges in graph convolutional networks for node classification'. Together they form a unique fingerprint.

Cite this