ReaLitE: Enrichment of Relation Embeddings in Knowledge Graphs using Numeric Literals
This addresses the issue of incomplete numerical data in real-world knowledge graphs for researchers and practitioners in AI, though it is incremental as it builds on existing KGE methods.
The paper tackled the problem of knowledge graph embedding methods ignoring numerical literals, which can lead to information loss, by proposing ReaLitE, a relation-centric model that dynamically aggregates numerical attributes with relation embeddings, achieving state-of-the-art results in link prediction and node classification tasks.
Most knowledge graph embedding (KGE) methods tailored for link prediction focus on the entities and relations in the graph, giving little attention to other literal values, which might encode important information. Therefore, some literal-aware KGE models attempt to either integrate numerical values into the embeddings of the entities or convert these numerics into entities during preprocessing, leading to information loss. Other methods concerned with creating relation-specific numerical features assume completeness of numerical data, which does not apply to real-world graphs. In this work, we propose ReaLitE, a novel relation-centric KGE model that dynamically aggregates and merges entities' numerical attributes with the embeddings of the connecting relations. ReaLitE is designed to complement existing conventional KGE methods while supporting multiple variations for numerical aggregations, including a learnable method. We comprehensively evaluated the proposed relation-centric embedding using several benchmarks for link prediction and node classification tasks. The results showed the superiority of ReaLitE over the state of the art in both tasks.