Header

UZH-Logo

Maintenance Infos

Interaction Embeddings for Prediction and Explanation in Knowledge Graphs


Zhang, Wen; Paudel, Bibek; Zhang, Wei; Bernstein, Abraham; Chen, Huajun (2019). Interaction Embeddings for Prediction and Explanation in Knowledge Graphs. In: International Conference on Web Search and Data Mining (WSDM), Melbourne, 11 February 2019 - 15 February 2019.

Abstract

Knowledge graph embedding aims to learn distributed representations for entities and relations, and are proven to be effective in many applications. Crossover interactions --- bi-directional effects between entities and relations --- help select related information when predicting a new triple, but hasn't been formally discussed before.
In this paper, we propose CrossE, a novel knowledge graph embedding which explicitly simulates crossover interactions. It not only learns one general embedding for each entity and relation as in most previous methods, but also generates multiple triple specific embeddings for both of them, named interaction embeddings.
We evaluate the embeddings on typical link prediction task and find that CrossE achieves state-of-the-art results on complex and more challenging datasets.
Furthermore, we evaluate the embeddings from a new perspective --- giving explanations for predicted triples, which is important for real applications.
In this work, explanations for a triple are regarded as reliable closed-paths between head and tail entity. Compared to other baselines, we show experimentally that CrossE is more capable of generating reliable explanations to support its predictions, benefiting from interaction embeddings.

Abstract

Knowledge graph embedding aims to learn distributed representations for entities and relations, and are proven to be effective in many applications. Crossover interactions --- bi-directional effects between entities and relations --- help select related information when predicting a new triple, but hasn't been formally discussed before.
In this paper, we propose CrossE, a novel knowledge graph embedding which explicitly simulates crossover interactions. It not only learns one general embedding for each entity and relation as in most previous methods, but also generates multiple triple specific embeddings for both of them, named interaction embeddings.
We evaluate the embeddings on typical link prediction task and find that CrossE achieves state-of-the-art results on complex and more challenging datasets.
Furthermore, we evaluate the embeddings from a new perspective --- giving explanations for predicted triples, which is important for real applications.
In this work, explanations for a triple are regarded as reliable closed-paths between head and tail entity. Compared to other baselines, we show experimentally that CrossE is more capable of generating reliable explanations to support its predictions, benefiting from interaction embeddings.

Statistics

Downloads

541 downloads since deposited on 18 Feb 2019
541 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:15 February 2019
Deposited On:18 Feb 2019 09:05
Last Modified:29 Apr 2019 07:31
Publisher:Association of Computing Machinery (ACM)
OA Status:Green
Other Identification Number:merlin-id:16969

Download

Download PDF  'Interaction Embeddings for Prediction and Explanation in Knowledge Graphs'.
Preview
Content: Published Version
Filetype: PDF
Size: 1MB