Probabilistic learning on graphs via contextual architectures

MaRDI QIDQ4969243zbMATH OpenFDO

Authors Davide Bacciu, Federico Errica, Alessio Micheli

Publication date 5 October 2020

Full work available at URL https://jmlr.csail.mit.edu/papers/v21/19-470.html

zbMATH Keywords

deep graph networksdeep learninggraph classificationgraph neural networksmaximum likelihoodnode classificationstructured domains

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A gentle introduction to deep learning for graphs
• Graph deconvolutional networks
• Graph Representation Learning
• Locality preserving dense graph convolutional networks with graph context-aware node representations
• \textsc{gat2vec}: representation learning for attributed graphs

Cites work

• A gentle introduction to deep learning for graphs
• Graph kernels
• scientific article; zbMATH DE number 1222290 (Why is no real title available?)
• kLog: a language for logical and relational learning with kernels
• Mixed memory Markov models: Decomposing complex stochastic processes as mixtures of simpler ones
• Pattern recognition and machine learning.
• Weisfeiler-Lehman graph kernels

Cited in

(6)

• A generalized Weisfeiler-Lehman graph kernel
• Graph deconvolutional networks
• Learning Generative Graph Prototypes Using Simplified von Neumann Entropy
• Learning of Multimodal Representations With Random Walks on the Click Graph
• Multi-graph fusion graph convolutional networks with pseudo-label supervision
• A probabilistic model for node classification in directed graphs

Describes a project that uses

Uses Software

• GMNN
• PyTorch
• Adam
• NetKit
• struc2vec

This page was built for publication: Probabilistic learning on graphs via contextual architectures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969243)