Titlebook: Structural, Syntactic, and Statistical Pattern Recognition; Joint IAPR Internati Adam Krzyzak,Ching Y. Suen,Nicola Nobile Conference procee

全能

,Maximal Independent Vertex Set Applied to Graph Pooling,ing a Maximal Independent Vertex Set (MIVS) and an assignment of the remaining vertices to the survivors. Consequently, our method does not discard any vertex information nor artificially increase the density of the graph. Experimental results show an increase in accuracy for graph classification on various standard datasets.

Deject

Stricture

anaphylaxis

,Graph Reduction Neural Networks for Structural Pattern Recognition,k. Eventually, we use the reduced graphs in conjunction with graph edit distance and a distance-based classifier. On five datasets we empirically confirm the benefit of the novel reduction scheme regarding both classification performance and computation time.

Foam-Cells

exceptional

巡回

cruise

蛰伏

,A Novel Graph Kernel Based on the Wasserstein Distance and Spectral Signatures,f the node feature (if available) and we define a kernel between two input graphs in terms of the Wasserstein distance between the respective node embeddings. Experiments on standard graph classification benchmarks show that our kernel performs favourably when compared to widely used alternative kernels as well as graph neural networks.

窝转脊椎动物