Yangzhe Peng

Yangzhe Peng

Auto-generated profile, based on publicly available information

Yangzhe Peng

School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China

Research Focus & Metrics

Academic Career Length

30Years (1997-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

1 July 1997
Verified
Conference Paper
Closed access
MEM. Elhasnaoui
M. Elhasnaoui
YPY. Peng
Y. Peng
RHR. Hanus
R. Hanus

10 April 2026 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
GLGaichao Li
Gaichao Li
JCJinsong Chen
Jinsong Chen
YPYangzhe Peng
Yangzhe Peng
KHKun He
Kun He
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.

3 August 2025
Verified
Conference Paper
Open access
YPYangzhe Peng
Yangzhe Peng
KGKaiyuan Gao
Kaiyuan Gao
LHLiang He
Liang He
YCYuheng Cong
Yuheng Cong
HLHaiguang Liu
Haiguang Liu
LWLijun Wu
Lijun Wu