AICLOct 26, 2021

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

arXiv:2110.13715v2149 citationsHas Code
Originality Highly original
AI Analysis

This addresses a limitation in knowledge graph reasoning for applications requiring complex logical queries, though it is incremental as it extends prior geometry-based methods.

The paper tackled the challenge of modeling queries with negation in geometry-based query embedding for multi-hop reasoning over knowledge graphs, and the result was that ConE significantly outperformed existing state-of-the-art methods on benchmark datasets.

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 Cone Embeddings (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 Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes