PathE: Leveraging Entity-Agnostic Paths for Parameter-Efficient Knowledge Graph Embeddings

TL;DR

PathE introduces a scalable, parameter-efficient knowledge graph embedding model that computes entity representations from relation paths, achieving state-of-the-art results with significantly fewer parameters and less computational resources.

Contribution

PathE is the first model to learn entity embeddings via relation paths without storing entity tables, reducing parameters and computational costs.

Findings

Achieves state-of-the-art relation prediction performance.

Maintains competitive link prediction on path-rich KGs.

Uses less than 25% of the parameters compared to previous methods.

Abstract

Knowledge Graphs (KGs) store human knowledge in the form of entities (nodes) and relations, and are used extensively in various applications. KG embeddings are an effective approach to addressing tasks like knowledge discovery, link prediction, and reasoning. This is often done by allocating and learning embedding tables for all or a subset of the entities. As this scales linearly with the number of entities, learning embedding models in real-world KGs with millions of nodes can be computationally intractable. To address this scalability problem, our model, PathE, only allocates embedding tables for relations (which are typically orders of magnitude fewer than the entities) and requires less than 25% of the parameters of previous parameter efficient methods. Rather than storing entity embeddings, we learn to compute them by leveraging multiple entity-relation paths to contextualise individual entities within triples. Evaluated on four benchmarks, PathE achieves state-of-the-art performance in relation prediction, and remains competitive in link prediction on path-rich KGs while training on consumer-grade hardware. We perform ablation experiments to test our design choices and analyse the sensitivity of the model to key hyper-parameters. PathE is efficient and cost-effective for relationally diverse and well-connected KGs commonly found in real-world applications.