Multi-relational graph convolutional networks: generalization guarantees and experiments

DOI10.1016/J.NEUNET.2023.01.044MaRDI QIDQ6488824zbMATH OpenFDO

Authors Xutao Li, Michael Ng, Guangning Xu, Andy M. Yip

Publication date 26 October 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.NEUNET.2023.01.044

zbMATH Keywords

algorithmic stabilitygraph convolutional networksmulti-relational datageneralization guarantees

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Multilinear algebra, tensor calculus (15A69)

Recommendations

• Tensor Graph Convolutional Networks for Multi-Relational and Robust Learning
• Relation-aware Graph Contrastive Learning
• Beyond graph neural networks with lifted relational neural networks
• Multi-graph fusion graph convolutional networks with pseudo-label supervision
• Graph neural networks: foundations, frontiers, and applications
• Graph kernels and Gaussian processes for relational reinforcement learning
• A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinations

Cites work

• 10.1162/153244302760200704
• Factorization strategies for third-order tensors
• Learning Theory
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization

Cited in

(1)

• Propagation on multi-relational graphs for node regression

This page was built for publication: Multi-relational graph convolutional networks: generalization guarantees and experiments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6488824)