Graph-Based Representations in Pattern Recognition〈1st ed. 2023〉 : 13th IAPR-TC-15 International Workshop, GbRPR 2023, Vietri sul Mare, Italy, September 6–8, 2023, Proceedings

著者名：Vento, Mario (EDT)/Foggia, Pasquale (EDT)/Conte, Donatello (EDT)/Carletti, Vincenzo (EDT)

Springer（2023/08/23発売）

• 言語：ENG
• ISBN：9783031427947
• eISBN：9783031427954

Description

This book constitutes the refereed proceedings of the 13th IAPR-TC-15 International Workshop on Graph-Based Representations in Pattern Recognition, GbRPR 2023, which took place in Vietri sul Mare, Italy, in September 2023.

The 16 full papers included in this book were carefully reviewed and selected from 18 submissions. They were organized in topical sections on graph kernels and graph algorithms; graph neural networks; and graph-based representations and applications.

Table of Contents

Graph Kernels and Graph Algorithms.- Quadratic Kernel Learning for Interpolation Kernel Machine Based Graph Classification.- Minimum Spanning Set Selection in Graph Kernels.- Graph-based vs. Vector-based Classification: A Fair Comparison.- A Practical Algorithm for Max-Norm Optimal Binary Labeling of Graphs.- Efficient Entropy-based Graph Kernel.- Graph Neural Networks.- GNN-DES: A new end-to-end dynamic ensemble selection method based on multi-label graph neural network.- C2N-ABDP: Cluster-to-Node Attention-based Differentiable Pooling.- Splitting Structural and Semantic Knowledge in Graph Autoencoders

for Graph Regression.- Graph Normalizing Flows to Pre-image Free Machine Learning for Regression.- Matching-Graphs for Building Classification Ensembles.- Maximal Independent Sets for Pooling in Graph Neural Networks.- Graph-based Representations and Applications.- Detecting Abnormal Communication Patterns in IoT Networks Using Graph Neural Networks.- Cell segmentation of in situ transcriptomics data using signed graph partitioning.- Graph-based representation for multi-image super-resolution.- Reducing the Computational Complexity of the Eccentricity Transform.- Graph-Based Deep Learning on the Swiss River Network.