PathE: Leveraging Entity-Agnostic Paths for Parameter-Efficient Knowledge Graph Embeddings
This addresses the computational intractability of embedding models for real-world knowledge graphs with millions of nodes, making it more efficient for applications like knowledge discovery and reasoning.
The paper tackles the scalability problem of knowledge graph embeddings by proposing PathE, which allocates embeddings only for relations instead of entities, reducing parameters by over 75% compared to previous methods. It achieves state-of-the-art performance in relation prediction and remains competitive in link prediction on path-rich knowledge graphs.
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.