Composition-based Multi-Relational Graph Convolutional Networks (2019-11-08T00:00:00.000000Z)

TL;DR

This paper proposes CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph and leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations.

Abstract

Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research.

Authors

P. Talukdar

8 papers

Shikhar Vashishth

4 papers

Soumya Sanyal

2 papers

TL;DR

Abstract

Authors

References55 items

A Re-evaluation of Knowledge Graph Completion Methods

InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions

A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment

Adaptive Convolution for Multi-Relational Learning

Fast Graph Representation Learning with PyTorch Geometric

Confidence-based Graph Convolutional Networks for Semi-Supervised Learning

RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction

End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion

How Powerful are Graph Neural Networks?

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks

Hypernetwork Knowledge Graph Embeddings

Dating Documents using Graph Convolution Networks

Graph-to-Sequence Learning using Gated Graph Neural Networks

Dual-Primal Graph Convolutional Networks

Lovasz Convolutional Networks

An End-to-End Deep Learning Architecture for Graph Classification

A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network

Knowledge Graph Embedding: A Survey of Approaches and Applications

Protein Interface Prediction using Graph Convolutional Networks

KBGAN: Adversarial Learning for Knowledge Graph Embeddings

Graph Attention 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

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

RDF2Vec: RDF Graph Embeddings for Data Mining

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

Semi-Supervised Classification with Graph Convolutional Networks

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Complex Embeddings for Simple Link Prediction

Learning Convolutional Neural Networks for Graphs

Holographic Embeddings of Knowledge Graphs

Deep Graph Kernels

Observed versus latent features for knowledge base and text inference

A Review of Relational Machine Learning for Knowledge Graphs

Adam: A Method for Stochastic Optimization

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

Knowledge Graph Embedding by Translating on Hyperplanes

Question Answering with Subgraph Embeddings

Spectral Networks and Locally Connected Networks on Graphs

Translating Embeddings for Modeling Multi-relational Data

Reasoning With Neural Tensor Networks for Knowledge Base Completion

ImageNet classification with deep convolutional neural networks

Unsupervised generation of data mining features from linked open data

Supporting Linked Data Production for Cultural Heritage Institutes: The Amsterdam Museum Case Study

Weisfeiler-Lehman Graph Kernels

Understanding the difficulty of training deep feedforward neural networks

Long Short-Term Memory

The Predictive Toxicology Evaluation Challenge

WordNet: A Lexical Database for English

Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity.

for graph classiﬁcation, similar to Xu et al.

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names