RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphs

TL;DR

RConE is a novel embedding method designed for multi-hop logical query answering on multi-modal knowledge graphs, effectively incorporating multi-modal information and logical constructs to improve accuracy over existing models.

Contribution

It introduces the first logical query answering approach on MMKGs that handles sub-entities and multi-modal data, outperforming current state-of-the-art methods.

Findings

RConE outperforms existing models on four MMKG datasets.

The method effectively incorporates multi-modal information into logical query answering.

It is the first to handle sub-entities in logical queries over MMKGs.

Abstract

Multi-hop query answering over a Knowledge Graph (KG) involves traversing one or more hops from the start node to answer a query. Path-based and logic-based methods are state-of-the-art for multi-hop question answering. The former is used in link prediction tasks. The latter is for answering complex logical queries. The logical multi-hop querying technique embeds the KG and queries in the same embedding space. The existing work incorporates First Order Logic (FOL) operators, such as conjunction ($\wedge$), disjunction ($\vee$), and negation ($\neg$), in queries. Though current models have most of the building blocks to execute the FOL queries, they cannot use the dense information of multi-modal entities in the case of Multi-Modal Knowledge Graphs (MMKGs). We propose RConE, an embedding method to capture the multi-modal information needed to answer a query. The model first shortlists candidate (multi-modal) entities containing the answer. It then finds the solution (sub-entities) within those entities. Several existing works tackle path-based question-answering in MMKGs. However, to our knowledge, we are the first to introduce logical constructs in querying MMKGs and to answer queries that involve sub-entities of multi-modal entities as the answer. Extensive evaluation of four publicly available MMKGs indicates that RConE outperforms the current state-of-the-art.