Schema First! Learn Versatile Knowledge Graph Embeddings by Capturing Semantics with MASCHInE

TL;DR

This paper introduces MASCHInE, a novel approach that generates semantic-aware knowledge graph embeddings by leveraging protographs, resulting in more versatile and semantically meaningful embeddings for various tasks.

Contribution

It proposes a new method for creating semantic-rich KGEs through protograph heuristics, enhancing their versatility across multiple tasks.

Findings

Improved performance in entity clustering and node classification.

Increased semantically valid link predictions without sacrificing rank performance.

Demonstrated effectiveness across diverse evaluation benchmarks.

Abstract

Knowledge graph embedding models (KGEMs) have gained considerable traction in recent years. These models learn a vector representation of knowledge graph entities and relations, a.k.a. knowledge graph embeddings (KGEs). Learning versatile KGEs is desirable as it makes them useful for a broad range of tasks. However, KGEMs are usually trained for a specific task, which makes their embeddings task-dependent. In parallel, the widespread assumption that KGEMs actually create a semantic representation of the underlying entities and relations (e.g., project similar entities closer than dissimilar ones) has been challenged. In this work, we design heuristics for generating protographs -- small, modified versions of a KG that leverage RDF/S information. The learnt protograph-based embeddings are meant to encapsulate the semantics of a KG, and can be leveraged in learning KGEs that, in turn, also better capture semantics. Extensive experiments on various evaluation benchmarks demonstrate the soundness of this approach, which we call Modular and Agnostic SCHema-based Integration of protograph Embeddings (MASCHInE). In particular, MASCHInE helps produce more versatile KGEs that yield substantially better performance for entity clustering and node classification tasks. For link prediction, using MASCHinE substantially increases the number of semantically valid predictions with equivalent rank-based performance.