fuseGNN

Chen, Zhaodong; Yan, Mingyu; Zhu, Meng-Yang; Deng, Lei; Li, Guoqi; Li, Shuangchen; Xie, Yuan

doi:10.1145/3400302.3415610

Cited by 13 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Developing Processing Frameworks for HOGNNs. There exists a plethora of frameworks for GNNs [16], [18], [71], [79], [98], [132], [135], [140], [160], [161], [163], [172], [179], [231], [232], [238], [239], [241], [242], [246], [250], [272], [274], [278], [279], [283], [287]. A crucial direction would be to construct such frameworks for HOGNNs, focusing on research into system design and architecture, programmability, productivity, and others.…”

Section: 𝑂(|𝐸|)mentioning

confidence: 99%

Motif Prediction with Graph Neural Networks

Besta¹,

Grob²,

Miglioli³

et al. 2022

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

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. CCS CONCEPTS• Information systems → Data mining.

show abstract