Inclusion of domain-knowledge into GNNs using mode-directed inverse entailment

DOI10.1007/S10994-021-06090-8OpenAlexW3215004982MaRDI QIDQ2127250FDOQ2127250

Authors: Yanyan Li 

Publication date: 20 April 2022

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.10709

zbMATH Keywords

inductive logic programmingbackground knowledgegraph neural networksmode-directed inverse entailmentneuro-symbolic learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• kLog: a language for logical and relational learning with kernels
• Title not available (Why is that?)
• Graph kernels
• Title not available (Why is that?)
• Inductive Logic Programming: Theory and methods
• Lifted relational neural networks: efficient learning of latent relational structures
• What kinds of relational features are useful for statistical learning?
• Parameter screening and optimisation for ILP using designed experiments
• Incorporating symbolic domain knowledge into graph neural networks
• Beyond graph neural networks with lifted relational neural networks
• Graph Representation Learning
• 10.1162/153244304773633861
• Representation Learning
• Inductive Logic Programming

Uses Software

• kLog
• Aleph
• Keras
• PyTorch
• ImageNet
• Adam
• GNMT
• CLEVR dataset
• GitHub
• AlexNet
• WaveNet
• DL2
• CLEVR

This page was built for publication: Inclusion of domain-knowledge into GNNs using mode-directed inverse entailment

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2127250)