A Non-negative Factorization Approach to Node Pooling in Graph Convolutional Neural Networks
Authors:
- 12 November 2019
- book chapter
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 294-306
Abstract
No abstract availableKeywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Adaptive Clustering via Symmetric Nonnegative Matrix Factorization of the Similarity MatrixAlgorithms, 2019
- Adversarially Regularized Graph Autoencoder for Graph Embedding2018
- Generative Kernels for Tree-Structured DataIEEE Transactions on Neural Networks and Learning Systems, 2018
- Machine Learning Refined2016
- Compositional Generative Mapping for Tree-Structured Data—Part II: Topographic Projection ModelIEEE Transactions on Neural Networks and Learning Systems, 2012
- Neural Network for Graphs: A Contextual Constructive ApproachIEEE Transactions on Neural Networks, 2009
- Comparison of descriptor spaces for chemical compound retrieval and classificationKnowledge and Information Systems, 2007
- Protein function prediction via graph kernelsBioinformatics, 2005
- BRENDA, the enzyme database: updates and major new developmentsNucleic Acids Research, 2004
- Distinguishing Enzyme Structures from Non-enzymes Without AlignmentsJournal of Molecular Biology, 2003