Joint Link Prediction Via Inference from a Model

Parmis Naddaf, Erfaneh Mahmoudzaheh Ahmadi Nejad, Kiarash Zahirnia, Manfred Jaeger, Oliver Schulte

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review


A Joint Link Prediction Query (JLPQ) specifies a set of links to be predicted, given another set of links as well as node attributes as evidence. While single link prediction has been well studied in literature on deep graph learning, predicting multiple links together has gained little attention. This paper presents a novel framework for computing JLPQs using a probabilistic deep Graph Generative Model. Specifically, we develop inference procedures for an inductively trained Variational Graph Auto-Encoder (VGAE) that estimates the joint link probability for any input JLPQ, without
retraining. For evaluation, we apply inference to a range of joint link prediction queries on six benchmark datasets. We find that for most datasets and query types, joint link prediction via inference from a model achieves good predictive performance, better than the independent link prediction baselines (by 0.02-0.4 AUC points
depending on the dataset).
Original languageEnglish
Title of host publicationCIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
Number of pages10
PublisherAssociation for Computing Machinery
Publication date21 Oct 2023
ISBN (Electronic)979-8-4007-0124-5
Publication statusPublished - 21 Oct 2023
Event32nd ACM International Conference on Information and Knowledge Management - Birmingham, United Kingdom
Duration: 21 Oct 202325 Oct 2023


Conference32nd ACM International Conference on Information and Knowledge Management
Country/TerritoryUnited Kingdom


  • Graph Convolutional Networks
  • Graph Representation Learning
  • Inference from a Model
  • Link Prediction


Dive into the research topics of 'Joint Link Prediction Via Inference from a Model'. Together they form a unique fingerprint.

Cite this