ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Zhanqiu Zhang, Jie Wang, Jiajun Chen, Shuiwang Ji, Feng Wu

Keywords: Query Embeddings, Knowledge Graphs, Multi-hop Reasoning, Question Answering

TL;DR: A geometry-based query embedding model that can handle all first-order logical queries.

Abstract: Query embedding (QE)---which aims to embed entities and first-order logical (FOL) queries in low-dimensional spaces---has shown great power in multi-hop reasoning over knowledge graphs. Recently, embedding entities and queries with geometric shapes becomes a promising direction, as geometric shapes can naturally represent answer sets of queries and logical relationships among them. However, existing geometry-based models have difficulty in modeling queries with negation, which significantly limits their applicability. To address this challenge, we propose a novel query embedding model, namely \textbf{Con}e \textbf{E}mbeddings (ConE), which is the first geometry-based QE model that can handle all the FOL operations, including conjunction, disjunction, and negation. Specifically, ConE represents entities and queries as Cartesian products of two-dimensional cones, where the intersection and union of cones naturally model the conjunction and disjunction operations. By further noticing that the closure of complement of cones remains cones, we design geometric complement operators in the embedding space for the negation operations. Experiments demonstrate that ConE significantly outperforms existing state-of-the-art methods on benchmark datasets.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/MIRALab-USTC/QE-ConE

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2110.13715/code)