Graph-Based Representations in Pattern Recognition
Editat de Mario Vento, Pasquale Foggia, Donatello Conte, Vincenzo Carlettien Limba Engleză Paperback – 24 aug 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.
Preț: 343.41 lei
Preț vechi: 429.26 lei
-20% Nou
Puncte Express: 515
Preț estimativ în valută:
60.76€ • 70.78$ • 53.06£
60.76€ • 70.78$ • 53.06£
Carte tipărită la comandă
Livrare economică 19 ianuarie-02 februarie 26
Preluare comenzi: 021 569.72.76
Specificații
ISBN-13: 9783031427947
ISBN-10: 3031427947
Pagini: 200
Ilustrații: XVI, 184 p. 33 illus., 27 illus. in color.
Dimensiuni: 155 x 235 x 12 mm
Greutate: 0.31 kg
Ediția:1st edition 2023
Editura: Springer
Locul publicării:Cham, Switzerland
ISBN-10: 3031427947
Pagini: 200
Ilustrații: XVI, 184 p. 33 illus., 27 illus. in color.
Dimensiuni: 155 x 235 x 12 mm
Greutate: 0.31 kg
Ediția:1st edition 2023
Editura: Springer
Locul publicării:Cham, Switzerland
Cuprins
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.