en
Proceedings chapter
Open access
English

Motif Prediction with Graph Neural Networks

Presented at Washington DC (USA), 14-18/08/2022
PublisherACM
Publication date2022-08-14
First online date2022-08-14
Abstract

Link prediction is one of the central problems in graph mining. However, recent studies highlight the importance of higher-order network analysis, where complex structures called motifs are the first-class citizens. We first show that existing link prediction schemes fail to effectively predict motifs. To alleviate this, we establish a general motif prediction problem and we propose several heuristics that assess the chances for a specified motif to appear. To make the scores realistic, our heuristics consider – among others – correlations between links, i.e., the potential impact of some arriving links on the appearance of other links in a given motif. Finally, for highest accuracy, we develop a graph neural network (GNN) architecture for motif prediction. Our architecture offers vertex features and sampling schemes that capture the rich structural properties of motifs. While our heuristics are fast and do not need any training, GNNs ensure highest accuracy of predicting motifs, both for dense (e.g., 𝑘-cliques) and for sparse ones (e.g., 𝑘-stars). We consistently outperform the best available competitor by more than 10% on average and up to 32% in area under the curve. Importantly, the advantages of our approach over schemes based on uncorrelated link prediction increase with the increasing motif size and complexity. We also successfully apply our architecture for predicting more arbitrary clusters and communities, illustrating its potential for graph mining beyond motif analysis.

eng
Keywords
  • Motifs
  • Motif Prediction
  • Link Prediction
  • Graph Neural Network
Citation (ISO format)
BESTA, Maciej et al. Motif Prediction with Graph Neural Networks. In: KDD ’22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Washington DC (USA). [s.l.] : ACM, 2022. p. 35–45. doi: 10.1145/3534678.3539343
Main files (1)
Proceedings chapter (Published version)
Identifiers
ISBN9781450393850
5views
25downloads

Technical informations

Creation05/11/2023 6:27:26 AM
First validation05/15/2023 7:35:12 AM
Update time05/15/2023 7:35:12 AM
Status update05/15/2023 7:35:12 AM
Last indexation08/31/2023 11:11:36 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack