Query2Particles: Knowledge Graph Reasoning with Particle Embeddings

TL;DR

Query2Particles introduces a novel approach for knowledge graph reasoning by encoding complex queries into multiple particle embeddings, enabling more diverse answer retrieval and achieving state-of-the-art results on standard benchmarks.

Contribution

The paper proposes Query2Particles, a method that encodes queries into multiple particles to improve answer diversity and reasoning in knowledge graph query answering.

Findings

Achieves state-of-the-art performance on FB15k, FB15K-237, and NELL datasets.

Effectively retrieves diverse answers using multiple particle embeddings.

Supports complex first-order logic queries with neural logic operations.

Abstract

Answering complex logical queries on incomplete knowledge graphs (KGs) with missing edges is a fundamental and important task for knowledge graph reasoning. The query embedding method is proposed to answer these queries by jointly encoding queries and entities to the same embedding space. Then the answer entities are selected according to the similarities between the entity embeddings and the query embedding. As the answers to a complex query are obtained from a combination of logical operations over sub-queries, the embeddings of the answer entities may not always follow a uni-modal distribution in the embedding space. Thus, it is challenging to simultaneously retrieve a set of diverse answers from the embedding space using a single and concentrated query representation such as a vector or a hyper-rectangle. To better cope with queries with diversified answers, we propose Query2Particles (Q2P), a complex KG query answering method. Q2P encodes each query into multiple vectors, named particle embeddings. By doing so, the candidate answers can be retrieved from different areas over the embedding space using the maximal similarities between the entity embeddings and any of the particle embeddings. Meanwhile, the corresponding neural logic operations are defined to support its reasoning over arbitrary first-order logic queries. The experiments show that Query2Particles achieves state-of-the-art performance on the complex query answering tasks on FB15k, FB15K-237, and NELL knowledge graphs.