2014/01/01 by Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti
Computer Science · Mathematics · #Advanced Graph Neural Networks #Algorithm #Artificial intelligence #Bayesian Modeling and Causal Inference #Computer science #Discrete mathematics #Graph #Graph Theory and Algorithms #Graph isomorphism #Isomorphism (crystallography) #Kernel (algebra) #Line graph #Mathematics #Node (physics) #Test set #Theoretical computer science #cs.AI #cs.LG
paper · pdf · doi:10.1007/978-3-319-12640-1_12
published as Neural Information Processing, Volume 8835 of the series Lecture Notes in Computer Science pp 93-100, 2014 Springer International Publishing
openalex publication_date 2014/01/01 · arxiv created 2015/09/22 · arxiv updated 2015/09/23 · openalex created_date 2016/06/24 · openalex updated_date 2026/08/05
In this paper we present a novel graph kernel framework inspired the by the Weisfeiler-Lehman (WL) isomorphism tests. Any WL test comprises a relabelling phase of the nodes based on test-specific information extracted from the graph, for example the set of neighbours of a node. We defined a novel relabelling and derived two kernels of the framework from it. The novel kernels are very fast to compute and achieve state-of-the-art results on five real-world datasets.