Cheng Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Cheng Yan has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Feng Zhao
Natural Language Processing and Knowledge Graph Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China
6 shared publications - Hai Jin
Huazhong University of Science and Technology
2 shared publications - Hong Zhang
School of Computer Science and Technology Natural Language Processing and Knowledge Graph Lab Huazhong University of Science and Technology Wuhan China
1 shared publication - Hongzhi Zou
School of Computer Science and Technology Natural Language Processing and Knowledge Graph Lab Huazhong University of Science and Technology Wuhan China
1 shared publication Hui Lin
College of Urban Construction, Jiangxi Normal University, Nanchang 330022, China
1 shared publication- Lifang He
Department of Computer Science and Engineering, Lehigh University, Bethlehem, USA
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 12656-12666
Inductive Reasoning on Few-Shot Knowledge Graphs with Task-Aware Language Models
Cheng Yan, Feng Zhao, Ruilin Zhao, Hong Zhang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 12656-12666
Open AccessInductive Reasoning on Few-Shot Knowledge Graphs with Task-Aware Language Models
Cheng Yan, Feng Zhao, Ruilin Zhao, Hong Zhang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 3 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 11 (3) , 1321-1333
Multi-View Few-Shot Reasoning for Emerging Entities in Knowledge Graphs
A knowledge graph (KG) is a form of representing knowledge of the objective world. With the expansion of knowledge, KGs frequently incorporate new entities, which often possess limited associated data, known as few-shot features. Addressing the missing knowledge for these emerging entities is crucial practically, but there are significant challenges due to data scarcity. Previously developed methods based on knowledge graph embedding (KGE) and graph neural networks (GNNs) focusing on instance-level KGs are confronted with challenges of data scarcity and model simplicity, rendering them inapplicable to reasoning tasks in few-shot scenarios. To tackle these issues, we propose a multi-view few-shot KG reasoning method for emerging entities. The primary focus of our method lies in resolving the problem of link prediction for emerging entities with limited associated triples from multiple perspectives. Distinct from previous methods, our approach initially abstracts a concept-view KG from the conventional instance-view KG, enabling the formulation of commonsense rules. Additionally, we employ the aggregation of multi-hop subgraph features to enhance the representation of emerging entities. Furthermore, we introduce a more efficient cross-domain negative sampling strategy and a multi-view triple scoring function based on commonsense rules. Our experimental evaluations highlight the effectiveness of our method in few-shot contexts, demonstrating its robustness and adaptability in both cross-shot and zero-shot scenarios, significantly outperforming existing models in these challenging settings.
- 3 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 11 (3) , 1321-1333
Multi-View Few-Shot Reasoning for Emerging Entities in Knowledge Graphs
A knowledge graph (KG) is a form of representing knowledge of the objective world. With the expansion of knowledge, KGs frequently incorporate new entities, which often possess limited associated data, known as few-shot features. Addressing the missing knowledge for these emerging entities is crucial practically, but there are significant challenges due to data scarcity. Previously developed methods based on knowledge graph embedding (KGE) and graph neural networks (GNNs) focusing on instance-level KGs are confronted with challenges of data scarcity and model simplicity, rendering them inapplicable to reasoning tasks in few-shot scenarios. To tackle these issues, we propose a multi-view few-shot KG reasoning method for emerging entities. The primary focus of our method lies in resolving the problem of link prediction for emerging entities with limited associated triples from multiple perspectives. Distinct from previous methods, our approach initially abstracts a concept-view KG from the conventional instance-view KG, enabling the formulation of commonsense rules. Additionally, we employ the aggregation of multi-hop subgraph features to enhance the representation of emerging entities. Furthermore, we introduce a more efficient cross-domain negative sampling strategy and a multi-view triple scoring function based on commonsense rules. Our experimental evaluations highlight the effectiveness of our method in few-shot contexts, demonstrating its robustness and adaptability in both cross-shot and zero-shot scenarios, significantly outperforming existing models in these challenging settings.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 8 (5) , 3665-3677
From Concept to Instance: Hierarchical Reinforced Knowledge Graph Reasoning
The knowledge graph, a networked structure designed to organize the vast and heterogeneous knowledge existing in the real world, has gained widespread adoption as a background knowledge base for intelligent systems. Nevertheless, the incompleteness of knowledge graphs has been widely recognized as a significant challenge in their development and application. Recently, multi-hop knowledge graph reasoning has been an attractive method for completing a knowledge graph. The multi-hop knowledge graph reasoning based on the reinforcement learning (RL) framework has achieved promising performance in terms of interpretability and scalability. An RL agent automatically reasons over a KG under the guidance of a policy network. When faced with a query, obtaining the approximate range of the answer first and then delving into individual options is a more efficient approach compared to traversing all candidate answers. However, existing RL-based methods have two limitations. First, they lack the ability to filter candidate decisions, making it challenging to handle entities with a large number of neighbors. Second, they fail to consider the intrinsic correlations between entities. To address these limitations, we propose a novel hierarchical knowledge graph reasoning approach HiKGR , which leverages the concept information of entities. Specifically, HiKGR reconstructs the previous action space in RL into a concept space and an instance space, enabling two policies to alternate reasoning at the concept level and the instance level. Furthermore, we propose hierarchical reward functions for the two-level policies to achieve joint optimization. The hierarchical reasoning approach we propose is capable of selecting more reasonable candidate decisions and optimizing the decision space. Experimental results reveal that HiKGR significantly outperforms existing RL-based methods and drastically reduces the action space size.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 8 (5) , 3665-3677
From Concept to Instance: Hierarchical Reinforced Knowledge Graph Reasoning
The knowledge graph, a networked structure designed to organize the vast and heterogeneous knowledge existing in the real world, has gained widespread adoption as a background knowledge base for intelligent systems. Nevertheless, the incompleteness of knowledge graphs has been widely recognized as a significant challenge in their development and application. Recently, multi-hop knowledge graph reasoning has been an attractive method for completing a knowledge graph. The multi-hop knowledge graph reasoning based on the reinforcement learning (RL) framework has achieved promising performance in terms of interpretability and scalability. An RL agent automatically reasons over a KG under the guidance of a policy network. When faced with a query, obtaining the approximate range of the answer first and then delving into individual options is a more efficient approach compared to traversing all candidate answers. However, existing RL-based methods have two limitations. First, they lack the ability to filter candidate decisions, making it challenging to handle entities with a large number of neighbors. Second, they fail to consider the intrinsic correlations between entities. To address these limitations, we propose a novel hierarchical knowledge graph reasoning approach HiKGR , which leverages the concept information of entities. Specifically, HiKGR reconstructs the previous action space in RL into a concept space and an instance space, enabling two policies to alternate reasoning at the concept level and the instance level. Furthermore, we propose hierarchical reward functions for the two-level policies to achieve joint optimization. The hierarchical reasoning approach we propose is capable of selecting more reasonable candidate decisions and optimizing the decision space. Experimental results reveal that HiKGR significantly outperforms existing RL-based methods and drastically reduces the action space size.
- Open Access
- 17 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (6) , 1-21
BayesKGR: Bayesian Few-Shot Learning for Knowledge Graph Reasoning
Reasoning over knowledge graphs (KGs) has received increasing attention recently due to its promising applications in many areas, such as semantic search and recommendation systems. Subsequently, most reasoning models are inherently transductive and ignore uncertainties of KGs, making it difficult to generalize to unseen entities. Moreover, existing approaches usually require each entity in the KG to have sufficient training samples, which leads to the overfitting of the entity having few instances. In fact, long-tail distributions are quite widespread in KGs, and newly emerging entities will tend to have only a few related triples. In this work, we aim at studying knowledge graph reasoning under a challenging setting where only limited training samples are available. Specifically, we propose a Bayesian inductive reasoning method and incorporate meta-learning techniques in few-shot learning to solve data deficiency and uncertainties. We design a Bayesian graph neural network as a meta-learner to achieve Bayesian inference, which can extrapolate meta-knowledge from observed KG to emerging entities. We conduct extensive experiments on two large-scale benchmark datasets, and the results demonstrate considerable performance improvement with the proposed approach over other baselines.
- 17 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (6) , 1-21
Open AccessBayesKGR: Bayesian Few-Shot Learning for Knowledge Graph Reasoning
Reasoning over knowledge graphs (KGs) has received increasing attention recently due to its promising applications in many areas, such as semantic search and recommendation systems. Subsequently, most reasoning models are inherently transductive and ignore uncertainties of KGs, making it difficult to generalize to unseen entities. Moreover, existing approaches usually require each entity in the KG to have sufficient training samples, which leads to the overfitting of the entity having few instances. In fact, long-tail distributions are quite widespread in KGs, and newly emerging entities will tend to have only a few related triples. In this work, we aim at studying knowledge graph reasoning under a challenging setting where only limited training samples are available. Specifically, we propose a Bayesian inductive reasoning method and incorporate meta-learning techniques in few-shot learning to solve data deficiency and uncertainties. We design a Bayesian graph neural network as a meta-learner to achieve Bayesian inference, which can extrapolate meta-knowledge from observed KG to emerging entities. We conduct extensive experiments on two large-scale benchmark datasets, and the results demonstrate considerable performance improvement with the proposed approach over other baselines.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 8693-8703
Structure-aware Knowledge Graph-to-text Generation with Planning Selection and Similarity Distinction
Feng Zhao, Hongzhi Zou, Cheng Yan. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 8693-8703
Open AccessStructure-aware Knowledge Graph-to-text Generation with Planning Selection and Similarity Distinction
Feng Zhao, Hongzhi Zou, Cheng Yan. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 8 April 2022
- Published by Springer Nature
- p. 153-161
ExKGR: Explainable Multi-hop Reasoning for Evolving Knowledge Graph
- 8 April 2022
- Published by Springer Nature
- p. 153-161
ExKGR: Explainable Multi-hop Reasoning for Evolving Knowledge Graph
- Open Access
- 30 January 2022
- Published by Century Science Publishing Co in Journal of Social Science and Humanities
- Vol. 4 (1)
Research on Sustainable Development Strategy of Contemporary Inheritance Industry of Chinese Traditional Painting Art
- 30 January 2022
- Published by Century Science Publishing Co in Journal of Social Science and Humanities
- Vol. 4 (1)
Open AccessResearch on Sustainable Development Strategy of Contemporary Inheritance Industry of Chinese Traditional Painting Art