RMNA: A Neighbor Aggregation-Based Knowledge Graph Representation Learning Model Using Rule Mining

TL;DR

RMNA is a novel neighbor aggregation-based knowledge graph embedding model that leverages rule mining to incorporate multi-hop neighbor information effectively, improving upon existing models' limitations.

Contribution

RMNA introduces a rule mining approach to transform multi-hop neighbors into one-hop neighbors, enhancing information utilization in knowledge graph embeddings.

Findings

RMNA achieves competitive performance compared to state-of-the-art models.

Utilizing rule-mined multi-hop neighbors improves embedding quality.

The model effectively captures multi-hop relational information.

Abstract

Although the state-of-the-art traditional representation learning (TRL) models show competitive performance on knowledge graph completion, there is no parameter sharing between the embeddings of entities, and the connections between entities are weak. Therefore, neighbor aggregation-based representation learning (NARL) models are proposed, which encode the information in the neighbors of an entity into its embeddings. However, existing NARL models either only utilize one-hop neighbors, ignoring the information in multi-hop neighbors, or utilize multi-hop neighbors by hierarchical neighbor aggregation, destroying the completeness of multi-hop neighbors. In this paper, we propose a NARL model named RMNA, which obtains and filters horn rules through a rule mining algorithm, and uses selected horn rules to transform valuable multi-hop neighbors into one-hop neighbors, therefore, the information in valuable multi-hop neighbors can be completely utilized by aggregating these one-hop neighbors. In experiments, we compare RMNA with the state-of-the-art TRL models and NARL models. The results show that RMNA has a competitive performance.