Joint Use of Node Attributes and Proximity for Node Classification

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Node classification aims to infer unknown node labels from known labels and other node attributes. Standard approaches for this task assume homophily, whereby a node’s label is predicted from the labels of other nodes nearby in the network. However, there are also cases of networks where labels are better predicted from the individual attributes of each node rather than the labels of nearby nodes. Ideally, node classification methods should flexibly adapt to a range of settings wherein unknown labels are predicted either from labels of nearby nodes, or individual node attributes, or partly both. In this paper, we propose a principled approach, JANE, based on a generative probabilistic model that jointly weighs the role of attributes and node proximity via embeddings in predicting labels. Experiments on multiple network datasets demonstrate that JANE exhibits the desired combination of versatility and competitive performance compared to baselines.
Original languageEnglish
Title of host publicationCOMPLEX NETWORKS & THEIR APPLICATIONS X, VOL 2 : Complex Networks & Their Applications X
EditorsR.M. Benito, C. Cherifi, H. Cherifi, E. Moro, L.M. Rocha, M. Sales-Pardo
Number of pages12
PublisherSpringer, Cham
Publication date1 Jan 2022
ISBN (Print)978-3-030-93412-5
ISBN (Electronic)978-3-030-93413-2
Publication statusPublished - 1 Jan 2022
MoE publication typeA4 Article in conference proceedings
EventThe International Conference on Complex Networks and their Applications (2021) - Madrid, Spain
Duration: 30 Nov 20212 Dec 2021
Conference number: 10th

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X

Fields of Science

  • 113 Computer and information sciences
  • Node classification
  • Graph embeddings
  • Spectral graph analysis

Cite this