A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal

K Liang, L Meng, M Liu, Y Liu, W Tu… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Knowledge graph reasoning (KGR), aiming to deduce new facts from existing facts based on
mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research …

Towards foundation models for knowledge graph reasoning

M Galkin, X Yuan, H Mostafa, J Tang, Z Zhu - arxiv preprint arxiv …, 2023 - arxiv.org
Foundation models in language and vision have the ability to run inference on any textual
and visual inputs thanks to the transferable representations such as a vocabulary of tokens …

Incorporating anticipation embedding into reinforcement learning framework for multi-hop knowledge graph question answering

H Cui, T Peng, F **ao, J Han, R Han, L Liu - Information Sciences, 2023 - Elsevier
Multi-hop knowledge graph question answering (KGQA) aims to pinpoint answer entities by
reasoning across multiple triples in knowledge graphs (KGs). To enhance model …

CRFR: Improving conversational recommender systems via flexible fragments reasoning on knowledge graphs

J Zhou, B Wang, R He, Y Hou - Proceedings of the 2021 …, 2021 - aclanthology.org
Although paths of user interests shift in knowledge graphs (KGs) can benefit conversational
recommender systems (CRS), explicit reasoning on KGs has not been well considered in …

Step by step: A hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning

A Zhu, D Ouyang, S Liang, J Shao - Knowledge-Based Systems, 2022 - Elsevier
Recently, knowledge graph reasoning has sparked great interest in research community,
which aims at inferring missing information in triples and provides critical support to various …

Path-based multi-hop reasoning over knowledge graph for answering questions via adversarial reinforcement learning

H Cui, T Peng, R Han, J Han, L Liu - Knowledge-Based Systems, 2023 - Elsevier
Multi-hop knowledge graph question answering targets at pinpointing the answer entities by
inferring across multiple triples in knowledge graphs. To enhance model interpretability …

Investigating the challenges and prospects of construction models for dynamic knowledge graphs

M Farghaly, M Mounir, M Aref, SM Moussa - IEEE Access, 2024 - ieeexplore.ieee.org
Recently, Dynamic knowledge graphs (DKGs) have been considered the foundation stone
for several powerful knowledge-aware applications. DKG has a great advancement over …

Iterative rule-guided reasoning over sparse knowledge graphs with deep reinforcement learning

Y **a, M Lan, J Luo, X Chen, G Zhou - Information Processing & …, 2022 - Elsevier
In recent years, reasoning over knowledge graphs (KGs) has been widely adapted to
empower retrieval systems, recommender systems, and question answering systems …

Reinforcement learning with dynamic completion for answering multi-hop questions over incomplete knowledge graph

H Cui, T Peng, R Han, B Zhu, H Bi, L Liu - Information Processing & …, 2023 - Elsevier
Text-enhanced and implicit reasoning methods are proposed for answering questions over
incomplete knowledge graph (KG), whereas prior studies either rely on external resources …

Attention-based exploitation and exploration strategy for multi-hop knowledge graph reasoning

B Shang, Y Zhao, Y Liu, C Wang - Information Sciences, 2024 - Elsevier
Abstract Knowledge Graphs (KGs) typically suffer from incompleteness. A popular approach
to solve this problem is multi-hop reasoning through Reinforcement Learning (RL) …