Yangzhe Peng
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
Yangzhe Peng has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Kun He
Huazhong University of Science and Technology
2 shared publications R. Hanus
Laboratoire d'Automatique, Université Libre de Bruxelles, Brussels, Belgium
2 shared publications- Gaichao Li
School of Computer Science and Technology, Institute of Artificial Intelligence, Huazhong University of Science and Technology; and Hopcroft Center on Computing Science, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Haiguang Liu
Microsoft Research AI for Science, Beijing, China
1 shared publication - Jinsong Chen
Central China Normal University
1 shared publication - Kaiyuan Gao
HuaZhong University of Science and Technology, Wuhan, Hubei, China
1 shared publication
Latest Publications
- Open Access
- 10 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (4) , 1-25
Tokenized Heterogeneous Graph Transformer with Enhanced Local and Global Representation Learning
Graph Transformers have demonstrated superiority in handling complex heterogeneous graphs in recent years. However, existing models still face several inherent challenges: (1) reliance on manually designed meta-paths to encode explicit local graph heterogeneity; (2) inability to capture fine-grained global information from distant yet relevant nodes. To address these limitations, we introduce THFormer, a novel node tokenized heterogeneous graph Transformer that learns expressive node representations by incorporating local and global perspectives. From the local perspective, we employ multiple subsequences for different heterogeneous types to explicitly encode local semantic relations, eliminating the need for manually designed meta-paths. From the global perspective, we design a local masking and global sampling mechanism to construct global structural (semantic) sequences, effectively capturing fine-grained global structural (semantic) information. Subsequently, THFormer separately feeds the resulting global and local sequences into standard Transformer layers as model inputs. Since these sequences represent two distinct views of the same target node, their corresponding outputs are naturally aligned to generate self-supervisory signals for model training, further enhancing the expressiveness and reliability of the target node representation. Extensive experiments are conducted to validate the efficacy of THFormer, and the quantitative performance gains are 0.24%, 0.31%, 0.51%, and 0.81% on DBLP, ACM, IMDB, and Freebase, respectively. The experimental results demonstrate the superiority of THFormer over representative heterogeneous graph neural networks and graph Transformer models.
- 10 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (4) , 1-25
Open AccessTokenized Heterogeneous Graph Transformer with Enhanced Local and Global Representation Learning
Graph Transformers have demonstrated superiority in handling complex heterogeneous graphs in recent years. However, existing models still face several inherent challenges: (1) reliance on manually designed meta-paths to encode explicit local graph heterogeneity; (2) inability to capture fine-grained global information from distant yet relevant nodes. To address these limitations, we introduce THFormer, a novel node tokenized heterogeneous graph Transformer that learns expressive node representations by incorporating local and global perspectives. From the local perspective, we employ multiple subsequences for different heterogeneous types to explicitly encode local semantic relations, eliminating the need for manually designed meta-paths. From the global perspective, we design a local masking and global sampling mechanism to construct global structural (semantic) sequences, effectively capturing fine-grained global structural (semantic) information. Subsequently, THFormer separately feeds the resulting global and local sequences into standard Transformer layers as model inputs. Since these sequences represent two distinct views of the same target node, their corresponding outputs are naturally aligned to generate self-supervisory signals for model training, further enhancing the expressiveness and reliability of the target node representation. Extensive experiments are conducted to validate the efficacy of THFormer, and the quantitative performance gains are 0.24%, 0.31%, 0.51%, and 0.81% on DBLP, ACM, IMDB, and Freebase, respectively. The experimental results demonstrate the superiority of THFormer over representative heterogeneous graph neural networks and graph Transformer models.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2281-2290
CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2281-2290
Open AccessCovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions
- 24 August 2005
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2220-2221
Deadbeat controllers leading to overshoot and undershoot within prespecified bounds
- 24 August 2005
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2220-2221
Deadbeat controllers leading to overshoot and undershoot within prespecified bounds
- 1 July 1997
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1159-1164
Multivariable constrained receding horizon control
- 1 July 1997
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1159-1164
Multivariable constrained receding horizon control