Dechuang Chen
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
Research Interests
Dechuang Chen has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Sibo Wang
The Chinese University of Hong Kong, Hong Kong SAR, China
3 shared publications - Fangyuan Zhang
The Chinese University of Hong Kong, Hong Kong, Hong Kong
2 shared publications - Qintian Guo
Hong Kong University of Science and Technology, Hong Kong, Hong Kong
2 shared publications D.X. Li
Shenyang National Laboratory for Materials Science, Institute of Metal Research, Chinese Academy of Sciences, No. 72 Wenhua Road, Shenyang 110016, China
1 shared publication- Guanhao Hou
The Chinese University of Hong Kong, Hong Kong, Hong Kong
1 shared publication - Junhao Gan
The University of Melbourne, Melbourne, VIC, Australia
1 shared publication
Latest Publications
- Open Access
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
Concurrent Path-Copying Update to Tree Structures
Historical data are widely used in science, business, and web applications. In this context, tree structures play a fundamental role in databases, particularly in query processing. Path copying offers a cost-effective approach to providing immutable snapshots of a tree. If snapshots preserve the order of update requests, each snapshot version is mapped to a specific point in history, thereby facilitating historical data queries and analysis. Recently, Contreap enables concurrent path-copying updates on BSTs, primarily targeting historical queries on predefined statistics by maintaining the corresponding augments in tree nodes. However, real-world applications often require general-purpose operations, such as element retrieval or range scanning, while BSTs are not well-suited for such operations. Nevertheless, existing path-copying implementations for popular database tree structures generally lack efficient support for concurrent updates, limiting their applicability. In this paper, we present ConTree, a lightweight programming library that transparently supports concurrent path-copying updates for tree structures. We show how to integrate a recursive update process — subject to certain constraints to ensure correctness —,into ConTree. We further discuss techniques for optimising existing tree structures to improve the efficiency of concurrent path copying. Building on this foundation, we instantiate ART and B+Tree, addressing key obstacles to concurrent path copying with two novel solutions: AERT and BeTree, using our ConTree library. These optimised variants incorporate structural and algorithmic refinements to support scalable updates. Extensive experiments show that our concurrent update strategy is effective, delivering significant speedups for AERT and BeTree over their serial counterparts.
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
Open AccessConcurrent Path-Copying Update to Tree Structures
Historical data are widely used in science, business, and web applications. In this context, tree structures play a fundamental role in databases, particularly in query processing. Path copying offers a cost-effective approach to providing immutable snapshots of a tree. If snapshots preserve the order of update requests, each snapshot version is mapped to a specific point in history, thereby facilitating historical data queries and analysis. Recently, Contreap enables concurrent path-copying updates on BSTs, primarily targeting historical queries on predefined statistics by maintaining the corresponding augments in tree nodes. However, real-world applications often require general-purpose operations, such as element retrieval or range scanning, while BSTs are not well-suited for such operations. Nevertheless, existing path-copying implementations for popular database tree structures generally lack efficient support for concurrent updates, limiting their applicability. In this paper, we present ConTree, a lightweight programming library that transparently supports concurrent path-copying updates for tree structures. We show how to integrate a recursive update process — subject to certain constraints to ensure correctness —,into ConTree. We further discuss techniques for optimising existing tree structures to improve the efficiency of concurrent path copying. Building on this foundation, we instantiate ART and B+Tree, addressing key obstacles to concurrent path copying with two novel solutions: AERT and BeTree, using our ConTree library. These optimised variants incorporate structural and algorithmic refinements to support scalable updates. Extensive experiments show that our concurrent update strategy is effective, delivering significant speedups for AERT and BeTree over their serial counterparts.
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (6) , 1-26
ACGraph: An Efficient Asynchronous Out-of-Core Graph Processing Framework
Graphs are a ubiquitous data structure in diverse domains such as machine learning, social networks, and data mining. As real-world graphs continue to grow beyond the memory capacity of single machines, out-of-core graph processing systems have emerged as a viable solution. Yet, existing systems that rely on strictly synchronous, iteration-by-iteration execution incur significant overheads. In particular, their scheduling mechanisms lead to I/O inefficiencies, stemming from read and work amplification, and induce costly synchronization stalls hindering sustained disk utilization. To overcome these limitations, we present ACGraph, a novel asynchronous graph processing system optimized for SSD-based environments with constrained memory resources. ACGraph employs a dynamic, block-centric priority scheduler that adjusts in real time based on workload, along with an online asynchronous worklist that minimizes redundant disk accesses by efficiently reusing active blocks in memory. Moreover, ACGraph unifies asynchronous I/O with computation in a pipelined execution model that maintains sustained I/O activation, and leverages a highly optimized hybrid storage format to expedite access to low-degree vertices. We implement popular graph algorithms, such as Breadth-First Search (BFS), Weakly Connected Components (WCC), personalized PageRank (PPR), PageRank (PR), and k -core on ACGraph and demonstrate that ACGraph substantially outperforms state-of-the-art out-of-core graph processing systems in both runtime and I/O efficiency.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (6) , 1-26
Open AccessACGraph: An Efficient Asynchronous Out-of-Core Graph Processing Framework
Graphs are a ubiquitous data structure in diverse domains such as machine learning, social networks, and data mining. As real-world graphs continue to grow beyond the memory capacity of single machines, out-of-core graph processing systems have emerged as a viable solution. Yet, existing systems that rely on strictly synchronous, iteration-by-iteration execution incur significant overheads. In particular, their scheduling mechanisms lead to I/O inefficiencies, stemming from read and work amplification, and induce costly synchronization stalls hindering sustained disk utilization. To overcome these limitations, we present ACGraph, a novel asynchronous graph processing system optimized for SSD-based environments with constrained memory resources. ACGraph employs a dynamic, block-centric priority scheduler that adjusts in real time based on workload, along with an online asynchronous worklist that minimizes redundant disk accesses by efficiently reusing active blocks in memory. Moreover, ACGraph unifies asynchronous I/O with computation in a pipelined execution model that maintains sustained I/O activation, and leverages a highly optimized hybrid storage format to expedite access to low-degree vertices. We implement popular graph algorithms, such as Breadth-First Search (BFS), Weakly Connected Components (WCC), personalized PageRank (PPR), PageRank (PR), and k -core on ACGraph and demonstrate that ACGraph substantially outperforms state-of-the-art out-of-core graph processing systems in both runtime and I/O efficiency.
- Open Access
- 8 December 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (4) , 1-26
Scalable Approximate Butterfly and Bi-triangle Counting for Large Bipartite Networks
A bipartite graph is a graph that consists of two disjoint sets of vertices and only edges between vertices from different vertex sets. In this paper, we study the counting problems of two common types of em motifs in bipartite graphs: (i) butterflies (2x2 bicliques) and (ii) bi-triangles (length-6 cycles). Unlike most of the existing algorithms that aim to obtain exact counts, our goal is to obtain precise enough estimations of these counts in bipartite graphs, as such estimations are already sufficient and of great usefulness in various applications. While there exist approximate algorithms for butterfly counting, these algorithms are mainly based on the techniques designed for general graphs, and hence, they are less effective on bipartite graphs. Not to mention that there is still a lack of study on approximate bi-triangle counting. Motivated by this, we first propose a novel butterfly counting algorithm, called one-sided weighted sampling, which is tailored for bipartite graphs. The basic idea of this algorithm is to estimate the total butterfly count with the number of butterflies containing two randomly sampled vertices from the same side of the two vertex sets. We prove that our estimation is unbiased, and our technique can be further extended (non-trivially) for bi-triangle count estimation. Theoretical analyses under a power-law random bipartite graph model and extensive experiments on multiple large real datasets demonstrate that our proposed approximate counting algorithms can reach high accuracy, yet achieve up to three orders (resp. four orders) of magnitude speed-up over the state-of-the-art exact butterfly (resp. bi-triangle) counting algorithms. Additionally, we present an approximate clustering coefficient estimation framework for bipartite graphs, which shows a similar speed-up over the exact solutions with less than 1% relative error.
- 8 December 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (4) , 1-26
Open AccessScalable Approximate Butterfly and Bi-triangle Counting for Large Bipartite Networks
A bipartite graph is a graph that consists of two disjoint sets of vertices and only edges between vertices from different vertex sets. In this paper, we study the counting problems of two common types of em motifs in bipartite graphs: (i) butterflies (2x2 bicliques) and (ii) bi-triangles (length-6 cycles). Unlike most of the existing algorithms that aim to obtain exact counts, our goal is to obtain precise enough estimations of these counts in bipartite graphs, as such estimations are already sufficient and of great usefulness in various applications. While there exist approximate algorithms for butterfly counting, these algorithms are mainly based on the techniques designed for general graphs, and hence, they are less effective on bipartite graphs. Not to mention that there is still a lack of study on approximate bi-triangle counting. Motivated by this, we first propose a novel butterfly counting algorithm, called one-sided weighted sampling, which is tailored for bipartite graphs. The basic idea of this algorithm is to estimate the total butterfly count with the number of butterflies containing two randomly sampled vertices from the same side of the two vertex sets. We prove that our estimation is unbiased, and our technique can be further extended (non-trivially) for bi-triangle count estimation. Theoretical analyses under a power-law random bipartite graph model and extensive experiments on multiple large real datasets demonstrate that our proposed approximate counting algorithms can reach high accuracy, yet achieve up to three orders (resp. four orders) of magnitude speed-up over the state-of-the-art exact butterfly (resp. bi-triangle) counting algorithms. Additionally, we present an approximate clustering coefficient estimation framework for bipartite graphs, which shows a similar speed-up over the exact solutions with less than 1% relative error.
- 1 October 2009
- Published by Elsevier in Journal of Alloys and Compounds
- Vol. 485 (1-2) , 598-603
Electronic structure and optical properties of In doped SrTiO3/MgO(001)
- 1 October 2009
- Published by Elsevier in Journal of Alloys and Compounds
- Vol. 485 (1-2) , 598-603
Electronic structure and optical properties of In doped SrTiO3/MgO(001)
- 8 March 2007
- Published by American Physical Society (APS) in Physical Review B
- Vol. 75 (12) , 125409
First-principles study of the interfacial structures ofBy using a first-principles method, the theoretical analysis of six probable interface models points out that two of them with oxygen or magnesium vacancies in the interface are most stable. It is found in this work that besides O or Mg vacancies having to exist in this interface, the stability of an interface depends deeply on the atomic configuration of interface. Such a configuration in which each Au atom in the upper Au layer of interface bonds with each O atom in the MgO under layer is theoretically considered to be most stable. Nevertheless, these results need to be confirmed by experiments.- 8 March 2007
- Published by American Physical Society (APS) in Physical Review B
- Vol. 75 (12) , 125409
First-principles study of the interfacial structures ofBy using a first-principles method, the theoretical analysis of six probable interface models points out that two of them with oxygen or magnesium vacancies in the interface are most stable. It is found in this work that besides O or Mg vacancies having to exist in this interface, the stability of an interface depends deeply on the atomic configuration of interface. Such a configuration in which each Au atom in the upper Au layer of interface bonds with each O atom in the MgO under layer is theoretically considered to be most stable. Nevertheless, these results need to be confirmed by experiments.