Hypernetwork Knowledge Graph Embeddings

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness. Inferring missing relations (links) between entities (nodes) is the task of link prediction. A recent state-of-the-art approach to link prediction, ConvE, implements a convolutional neural network to extract features from concatenated subject and relation vectors. Whilst results are impressive, the method is unintuitive and poorly understood. We propose a hypernetwork architecture that generates simplified relation-specific convolutional filters that (i) outperforms ConvE and all previous approaches across standard datasets; and (ii) can be framed as tensor factorization and thus set within a well established family of factorization models for link prediction. We thus demonstrate that convolution simply offers a convenient computational means of introducing sparsity and parameter tying to find an effective trade-off between non-linear expressiveness and the number of parameters to learn.
Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions
PublisherSpringer International Publishing
Number of pages13
ISBN (Electronic)978-3-030-30493-5
ISBN (Print)978-3-030-30492-8
Publication statusE-pub ahead of print - 9 Sep 2019
Event28th International Conference on Artificial Neural Networks - Munich, Germany
Duration: 17 Sep 201919 Sep 2019

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743


Conference28th International Conference on Artificial Neural Networks
Abbreviated titleICANN 2019
Internet address


Dive into the research topics of 'Hypernetwork Knowledge Graph Embeddings'. Together they form a unique fingerprint.

Cite this