Kangfei Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kangfei Zhao has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
- Yu Rong
The Chinese University of Hong Kong, Hong Kong, China
12 shared publications - Jeffrey Xu Yu
The Chinese University of Hong Kong, Hong Kong, China
11 shared publications - Deli Zhao
DAMO Academy, Alibaba Group, Hangzhou, China and Hupan Lab, Hangzhou, China
5 shared publications - Hong Cheng
The Chinese University of Hong Kong, Hong Kong, China
5 shared publications - Rui Li
The Chinese University of Hong Kong, Hong Kong, China
5 shared publications - Ercan Engin Kuruoglu
Tsinghua University
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5235-5245
H-Mem: Hawkes-driven Adaptive Forgetting for Long-Horizon Agent Memory
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5235-5245
Open AccessH-Mem: Hawkes-driven Adaptive Forgetting for Long-Horizon Agent Memory
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8081-8085
Type-aware Prompting for Community Search over Heterogeneous Information Networks
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8081-8085
Open AccessType-aware Prompting for Community Search over Heterogeneous Information Networks
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6758-6768
Cimos: Cost-Effective Multi-Query Oriented Continuous Subgraph Matching
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6758-6768
Open AccessCimos: Cost-Effective Multi-Query Oriented Continuous Subgraph Matching
- Top Cited PapersOpen Access
- 22 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (15) , 1-35
A Survey of Graph Transformers: Architectures, Theories and Applications
Graph Transformers (GTs) have demonstrated a strong capability in modeling graph structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as over-smoothing and over-squashing. Recent studies have proposed diverse architectures, enhanced explainability, and practical applications for Graph Transformers. In light of these rapid developments, we conduct a comprehensive review of Graph Transformers, covering aspects such as their architectures, theoretical foundations, and applications. In this survey, we first categorize the architecture of Graph Transformers according to their strategies for processing structural information, including graph tokenization, positional encoding, structure-aware attention, and model ensemble. Then, from the theoretical perspective, we examine the expressivity of Graph Transformers in various discussed architectures and contrast them with other advanced graph learning algorithms to discover their connections. For applications, we organize the literature around four graph organization forms, from relational, geometric, dynamic to heterogeneous. A Practical Guidance table then maps architectural components to these graph forms by adoption frequency, so practitioners can narrow down which design families to consider for a given input structure. Lastly, we will discuss the current challenges and prospective directions in Graph Transformers for potential future research.
- 22 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (15) , 1-35
Top Cited PapersOpen AccessA Survey of Graph Transformers: Architectures, Theories and Applications
Graph Transformers (GTs) have demonstrated a strong capability in modeling graph structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as over-smoothing and over-squashing. Recent studies have proposed diverse architectures, enhanced explainability, and practical applications for Graph Transformers. In light of these rapid developments, we conduct a comprehensive review of Graph Transformers, covering aspects such as their architectures, theoretical foundations, and applications. In this survey, we first categorize the architecture of Graph Transformers according to their strategies for processing structural information, including graph tokenization, positional encoding, structure-aware attention, and model ensemble. Then, from the theoretical perspective, we examine the expressivity of Graph Transformers in various discussed architectures and contrast them with other advanced graph learning algorithms to discover their connections. For applications, we organize the literature around four graph organization forms, from relational, geometric, dynamic to heterogeneous. A Practical Guidance table then maps architectural components to these graph forms by adoption frequency, so practitioners can narrow down which design families to consider for a given input structure. Lastly, we will discuss the current challenges and prospective directions in Graph Transformers for potential future research.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1039-1050
PLACE: Prompt Learning for Attributed Community Search in Large Graphs
Attributed Community Search (ACS) aims to identify communities in an attributed graph with structural cohesiveness and attribute homogeneity for given queries. While algorithmic approaches often suffer from structural inflexibility and attribute irrelevance, recent years have witnessed a boom in learning-based approaches that employ Graph Neural Networks (GNNs) to simultaneously model structural and attribute information. To improve GNN efficacy and efficiency, these approaches adopt various techniques to refine the input graph and queries, including query-dependent node pruning and feature enhancement. However, these refinements are either detached from the end-to-end optimization with the backbone model, or impose additional burdens on training resources, limiting their adaptability and practical usage in diverse graphs. In this paper, we propose PLACE(Prompt Learning for Attributed Community Search), a graph prompt learning framework for ACS. Inspired by prompt-tuning in Natural Language Processing (NLP), PLACE constructs a query-specific prompt graph consisting of learnable attribute tokens and virtual node tokens, and inserts it into the original graph to form a prompt-augmented graph. The learned prompt tokens act as a bridge that enriches the query context within the graph, enabling the GNN to more effectively capture patterns of structural cohesiveness and attribute similarity pertinent to each query. We employ an alternating training paradigm to jointly optimize the prompt parameters and the GNN, and design a divide-and-conquer strategy that scales PLACEto million-scale graphs. Extensive experiments on 9 real-world graphs across 3 types of ACS queries demonstrate that PLACE outperforms 6 baselines, achieving an average F1 improvement of 14% over the state-of-the-art.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1039-1050
Open AccessPLACE: Prompt Learning for Attributed Community Search in Large Graphs
Attributed Community Search (ACS) aims to identify communities in an attributed graph with structural cohesiveness and attribute homogeneity for given queries. While algorithmic approaches often suffer from structural inflexibility and attribute irrelevance, recent years have witnessed a boom in learning-based approaches that employ Graph Neural Networks (GNNs) to simultaneously model structural and attribute information. To improve GNN efficacy and efficiency, these approaches adopt various techniques to refine the input graph and queries, including query-dependent node pruning and feature enhancement. However, these refinements are either detached from the end-to-end optimization with the backbone model, or impose additional burdens on training resources, limiting their adaptability and practical usage in diverse graphs. In this paper, we propose PLACE(Prompt Learning for Attributed Community Search), a graph prompt learning framework for ACS. Inspired by prompt-tuning in Natural Language Processing (NLP), PLACE constructs a query-specific prompt graph consisting of learnable attribute tokens and virtual node tokens, and inserts it into the original graph to form a prompt-augmented graph. The learned prompt tokens act as a bridge that enriches the query context within the graph, enabling the GNN to more effectively capture patterns of structural cohesiveness and attribute similarity pertinent to each query. We employ an alternating training paradigm to jointly optimize the prompt parameters and the GNN, and design a divide-and-conquer strategy that scales PLACEto million-scale graphs. Extensive experiments on 9 real-world graphs across 3 types of ACS queries demonstrate that PLACE outperforms 6 baselines, achieving an average F1 improvement of 14% over the state-of-the-art.
- 1 July 2026
- Published by Springer Nature in The VLDB Journal
- Vol. 35 (4) , 36
$\textsf{IACS}^{+}$: Inductive Attributed Community Search via Learning across Graphs- 1 July 2026
- Published by Springer Nature in The VLDB Journal
- Vol. 35 (4) , 36
$\textsf{IACS}^{+}$: Inductive Attributed Community Search via Learning across Graphs- 20 May 2026
- Published by Springer Nature in The VLDB Journal
- Vol. 35 (4) , 28
CardOOD: robust query-driven cardinality estimation under out-of-distribution
- 20 May 2026
- Published by Springer Nature in The VLDB Journal
- Vol. 35 (4) , 28
CardOOD: robust query-driven cardinality estimation under out-of-distribution
- 10 May 2026
- Published by Springer Nature
- p. 713-717
Investigating Machine Learning Models for Cardinality Estimation: An interactive Approach
- 10 May 2026
- Published by Springer Nature
- p. 713-717
Investigating Machine Learning Models for Cardinality Estimation: An interactive Approach
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 140-151
Faico: Faithful and Complete Knowledge Graph Augmented Reasoning
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 140-151
Open AccessFaico: Faithful and Complete Knowledge Graph Augmented Reasoning
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 881-891
ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
Graph Transformers (GTs) have emerged as a promising graph learning tool, leveraging their all-pair connected property to effectively capture global information. To address the over-smoothing problem in deep GNNs, global attention was initially introduced, eliminating the necessity for using deep GNNs. However, through empirical and theoretical analysis, we verify that the introduced global attention exhibits severe over-smoothing, causing node representations to become indistinguishable due to its inherent low-pass filtering. This effect is even stronger than that observed in GNNs. To mitigate this, we propose PageRank Transformer (ParaFormer), which features a PageRank-enhanced attention module designed to mimic the behavior of deep Transformers. We theoretically and empirically demonstrate that ParaFormer mitigates over-smoothing by functioning as an adaptive-pass filter. Experiments show that ParaFormer achieves consistent performance improvements across both node classification and graph classification tasks on 11 datasets ranging from thousands to millions of nodes, validating its efficacy. The supplementary material, including code and appendix, can be found in https://github.com/chaohaoyuan/ParaFormer.
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 881-891
Open AccessParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
Graph Transformers (GTs) have emerged as a promising graph learning tool, leveraging their all-pair connected property to effectively capture global information. To address the over-smoothing problem in deep GNNs, global attention was initially introduced, eliminating the necessity for using deep GNNs. However, through empirical and theoretical analysis, we verify that the introduced global attention exhibits severe over-smoothing, causing node representations to become indistinguishable due to its inherent low-pass filtering. This effect is even stronger than that observed in GNNs. To mitigate this, we propose PageRank Transformer (ParaFormer), which features a PageRank-enhanced attention module designed to mimic the behavior of deep Transformers. We theoretically and empirically demonstrate that ParaFormer mitigates over-smoothing by functioning as an adaptive-pass filter. Experiments show that ParaFormer achieves consistent performance improvements across both node classification and graph classification tasks on 11 datasets ranging from thousands to millions of nodes, validating its efficacy. The supplementary material, including code and appendix, can be found in https://github.com/chaohaoyuan/ParaFormer.