Modeling Relational Data with Graph Convolutional Networks

Published in

Extended Semantic Web Conference(2017)

External Links:

Generate Graph

TL;DR

It is shown that factorization models for link prediction such as DistMult can be significantly improved through the use of an R-GCN encoder model to accumulate evidence over multiple inference steps in the graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.

Abstract

Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and apply them to two standard knowledge base completion tasks: Link prediction (recovery of missing facts, i.e. subject-predicate-object triples) and entity classification (recovery of missing entity attributes). R-GCNs are related to a recent class of neural networks operating on graphs, and are developed specifically to handle the highly multi-relational data characteristic of realistic knowledge bases. We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification. We further show that factorization models for link prediction such as DistMult can be significantly improved through the use of an R-GCN encoder model to accumulate evidence over multiple inference steps in the graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.

Authors

M. Welling

17 papers

Rianne van den Berg

4 papers

Ivan Titov

9 papers

References54 items

FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

Stochastic Training of Graph Convolutional Networks

Convolutional 2D Knowledge Graph Embeddings

Inductive Representation Learning on Large Graphs

Neural Message Passing for Quantum Chemistry

Modeling Relational Data with Graph Convolutional Networks

Published in

Extended Semantic Web Conference(2017)

External Links:

Generate Graph

TL;DR

Abstract

Authors

M. Welling

17 papers

Rianne van den Berg

4 papers

Ivan Titov

9 papers

References54 items

FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

Stochastic Training of Graph Convolutional Networks

Convolutional 2D Knowledge Graph Embeddings

Inductive Representation Learning on Large Graphs

Neural Message Passing for Quantum Chemistry

Thomas Kipf

11 papers

M. Schlichtkrull

3 papers

Peter Bloem

1 papers

TL;DR

Abstract

Authors

References54 items

FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

Stochastic Training of Graph Convolutional Networks

Convolutional 2D Knowledge Graph Embeddings

Inductive Representation Learning on Large Graphs

Neural Message Passing for Quantum Chemistry

TL;DR

Abstract

Authors

References54 items

FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

Stochastic Training of Graph Convolutional Networks

Convolutional 2D Knowledge Graph Embeddings

Inductive Representation Learning on Large Graphs

Neural Message Passing for Quantum Chemistry

Variational Graph Auto-Encoders

RDF2Vec: RDF Graph Embeddings for Data Mining

A Collection of Benchmark Datasets for Systematic Evaluations of Machine Learning on the Semantic Web

Column Networks for Collective Classification

Semi-Supervised Classification with Graph Convolutional Networks

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Complex Embeddings for Simple Link Prediction

Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text

Learning Convolutional Neural Networks for Graphs

Theano: A Python framework for fast computation of mathematical expressions

Substructure counting graph kernels for machine learning from RDF data

Gated Graph Sequence Neural Networks

EsdRank: Connecting Query and Documents through External Semi-Structured Data

Holographic Embeddings of Knowledge Graphs

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Query Expansion with Freebase

Observed versus latent features for knowledge base and text inference

Question Answering over Freebase with Multi-Column Convolutional Neural Networks

Composing Relationships with Translations

Large-scale Simple Question Answering with Memory Networks

Traversing Knowledge Graphs in Vector Space

Modeling Relation Paths for Representation Learning of Knowledge Bases

Generating Quiz Questions from Knowledge Graphs

Compositional Vector Space Models for Knowledge Base Completion

Adam: A Method for Stochastic Optimization

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

Typed Tensor Decomposition of Knowledge Bases for Relation Extraction

Entity query feature expansion using knowledge base links

Knowledge-Based Question Answering as Machine Translation

Information Extraction over Structured Data: Question Answering with Freebase

Spectral Networks and Locally Connected Networks on Graphs

Translating Embeddings for Modeling Multi-relational Data

Reasoning With Neural Tensor Networks for Knowledge Base Completion

Distributed Representations of Words and Phrases and their Compositionality

Unsupervised generation of data mining features from linked open data

Tapping into knowledge base for concept feedback: leveraging conceptnet to improve search results for difficult queries

A Three-Way Model for Collective Learning on Multi-Relational Data

Weisfeiler-Lehman Graph Kernels

Tensor Decompositions and Applications

Extracting and composing robust features with denoising autoencoders

Kernel Methods for Mining Instance Data in Ontologies

A new model for learning in graph domains

The Expression of a Tensor or a Polyadic as a Sum of Products

Learning Knowledge Graphs for Question Answering through Conversational Dialog

Injecting Logical Background Knowledge into Embeddings for Relation Extraction

François Chollet. keras. https://github.com/fchollet/keras

International Conference on The Theory of Information Retrieval , pages 111 – 120

Relation Extraction with Matrix Factorization and Universal Schemas

The Graph Neural Network Model

Field of Study

Venue Information

Name

Type

URL

Alternate Names