activity
20222025
most citedType-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs

6 citations · 10 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI2025

Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs

Yanlin Song, Ben Liu, Víctor Gutiérrez-Basulto +5

Knowledge Graph Question Answering aims to answer natural language questions by reasoning over structured knowledge graphs. While large language models have advanced KGQA through t…

cs.AI2024

COTET: Cross-view Optimal Transport for Knowledge Graph Entity Typing

Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang +2

Knowledge graph entity typing (KGET) aims to infer missing entity type instances in knowledge graphs. Previous research has predominantly centered around leveraging contextual info…

cs.AI2024

HyperMono: A Monotonicity-aware Approach to Hyper-Relational Knowledge Representation

Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang +2

In a hyper-relational knowledge graph (HKG), each fact is composed of a main triple associated with attribute-value qualifiers, which express additional factual knowledge. The hype…

cs.AI2023

HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion

Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang +2

Hyper-relational knowledge graphs (HKGs) extend standard knowledge graphs by associating attribute-value qualifiers to triples, which effectively represent additional fine-grained…

cs.AI2022

Transformer-based Entity Typing in Knowledge Graphs

Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang +2

We investigate the knowledge graph entity typing task which aims at inferring plausible entity types. In this paper, we propose a novel Transformer-based Entity Typing (TET) approa…

cs.AI2022★ 6 cited

Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang +3

Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem as traditional subgraph matching methods are not capable to deal with noise and missing in…