Hongchao Qin
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
Hongchao Qin has a total of 75 co-authors. Here are the top co-authors by number of shared publications:
- Rong-Hua Li
Beijing Institute of Technology, Beijing, China
26 shared publications - Guoren Wang
Beijing Institute of Technology, Beijing, China
18 shared publications - Ye Yuan
Beijing Institute of Technology, Beijing, China
8 shared publications - Guang Zeng
Ant Group, Hangzhou, China
6 shared publications Guoren Wang
Beijing Institute of Technology, Beijing, China
4 shared publications- Xiang Wu
Beijing Institute of Technology, Beijing, China
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2986-2996
P riv M em : Privacy-Preserving Temporal Motif Mining over Cross-User Agent Memory Graphs
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2986-2996
Open AccessP riv M em : Privacy-Preserving Temporal Motif Mining over Cross-User Agent Memory Graphs
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2975-2985
FortMem: Secure Stateful Data Management for Long-Term LLM Agent Memory
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2975-2985
Open AccessFortMem: Secure Stateful Data Management for Long-Term LLM Agent Memory
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1291-1302
Bounded-Memory Aggregate Query Processing on Streaming Temporal Graphs
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1291-1302
Open AccessBounded-Memory Aggregate Query Processing on Streaming Temporal Graphs
- 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. 979-989
MemDTG: Dynamic Temporal Memory Graphs for Evidence-Admissible Agent Memory
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 979-989
Open AccessMemDTG: Dynamic Temporal Memory Graphs for Evidence-Admissible Agent Memory
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1679-1694
Effective Bug Detection in Graph Database Engines: An LLM-Based Approach
Graph database engines play a pivotal role in efficiently storing and managing graph data across various domains, including bioinformatics, knowledge graphs, and recommender systems. Graph databases must be accurate because errors lead to faulty analysis. Current bug-detection approaches are confined to specific graph query languages, limiting their applicabilities when handling graph database engines that use various graph query languages across various domains. Moreover, they require extensive prior knowledge to generate queries for detecting bugs. To address these challenges, we introduce DGDB, a novel paradigm harnessing large language models (LLM), such as ChatGPT, for comprehensive bug detection in graph database engines. DGDB leverages ChatGPT to generate high-quality queries for different graph query languages. It subsequently employs differential testing to identify bugs in graph database engines. We applied this paradigm to graph database engines based on Cypher, Gremlin, and SPARQL, and detected a total of 23 previously unknown wrong-result bugs. DGDB achieves at least 20.41% improvement in the non-empty-result query ratio and detects more than three times as many bugs as existing state-of-the-art methods on Cypher-based graph database engines, with further significant gains when employing more advanced LLM.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1679-1694
Effective Bug Detection in Graph Database Engines: An LLM-Based Approach
Graph database engines play a pivotal role in efficiently storing and managing graph data across various domains, including bioinformatics, knowledge graphs, and recommender systems. Graph databases must be accurate because errors lead to faulty analysis. Current bug-detection approaches are confined to specific graph query languages, limiting their applicabilities when handling graph database engines that use various graph query languages across various domains. Moreover, they require extensive prior knowledge to generate queries for detecting bugs. To address these challenges, we introduce DGDB, a novel paradigm harnessing large language models (LLM), such as ChatGPT, for comprehensive bug detection in graph database engines. DGDB leverages ChatGPT to generate high-quality queries for different graph query languages. It subsequently employs differential testing to identify bugs in graph database engines. We applied this paradigm to graph database engines based on Cypher, Gremlin, and SPARQL, and detected a total of 23 previously unknown wrong-result bugs. DGDB achieves at least 20.41% improvement in the non-empty-result query ratio and detects more than three times as many bugs as existing state-of-the-art methods on Cypher-based graph database engines, with further significant gains when employing more advanced LLM.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (2) , 1144-1158
GRPCI: Harnessing Temporal-Spatial Dynamics for Graph Representation Learning
Temporal interactions form the crux of numerous real-world scenarios, thus necessitating effective modeling in temporal graph representation learning. Despite extensive research within this domain, we identify a significant oversight in current methodologies: the temporal-spatial dynamics in graphs, encompassing both structural and temporal coherence, remain largely unaddressed. In an effort to bridge this research gap, we present a novel framework termed Graph Representation learning enhanced by Periodic and Community Interactions (GRPCI). GRPCI consists of two primary mechanisms devised explicitly to tackle the aforementioned challenge. Firstly, to utilize latent temporal dynamics, we propose a novel periodicity-based neighborhood aggregation mechanism that underscores neighbors engaged in a periodic interaction pattern. This mechanism seamlessly integrates the element of periodicity into the model. Secondly, to exploit structural dynamics, we design a novel contrastive-based local community representation learning mechanism. This mechanism features a heuristic dynamic contrastive pair sampling strategy aimed at enhancing the modeling of the latent distribution of local communities within the graphs. Through the incorporation of these two mechanisms, GRPCI markedly augments the performance of graph networks. Empirical evaluations, conducted via a temporal link prediction task across five real-life datasets, attest to the superior performance of GRPCI in comparison to existing state-of-the-art methodologies. The results of this study validate the efficacy of GRPCI, thereby establishing a new benchmark for future research in the field of temporal graph representation learning. Our findings underscore the importance of considering both temporal and structural consistency in temporal graph learning, and advocate for further exploration of this paradigm.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (2) , 1144-1158
GRPCI: Harnessing Temporal-Spatial Dynamics for Graph Representation Learning
Temporal interactions form the crux of numerous real-world scenarios, thus necessitating effective modeling in temporal graph representation learning. Despite extensive research within this domain, we identify a significant oversight in current methodologies: the temporal-spatial dynamics in graphs, encompassing both structural and temporal coherence, remain largely unaddressed. In an effort to bridge this research gap, we present a novel framework termed Graph Representation learning enhanced by Periodic and Community Interactions (GRPCI). GRPCI consists of two primary mechanisms devised explicitly to tackle the aforementioned challenge. Firstly, to utilize latent temporal dynamics, we propose a novel periodicity-based neighborhood aggregation mechanism that underscores neighbors engaged in a periodic interaction pattern. This mechanism seamlessly integrates the element of periodicity into the model. Secondly, to exploit structural dynamics, we design a novel contrastive-based local community representation learning mechanism. This mechanism features a heuristic dynamic contrastive pair sampling strategy aimed at enhancing the modeling of the latent distribution of local communities within the graphs. Through the incorporation of these two mechanisms, GRPCI markedly augments the performance of graph networks. Empirical evaluations, conducted via a temporal link prediction task across five real-life datasets, attest to the superior performance of GRPCI in comparison to existing state-of-the-art methodologies. The results of this study validate the efficacy of GRPCI, thereby establishing a new benchmark for future research in the field of temporal graph representation learning. Our findings underscore the importance of considering both temporal and structural consistency in temporal graph learning, and advocate for further exploration of this paradigm.
- Open Access
δ-EMG: A Monotonic Graph Index for Approximate Nearest Neighbor Search
Approximate nearest neighbor (ANN) search in high-dimensional spaces is a foundational component of many modern retrieval and recommendation systems. Currently, almost all algorithms follow an $ε$-Recall-Bounded principle when comparing performance: they require the ANN search results to achieve a recall of more than $1-ε$ and then compare query-per-second (QPS) performance. However, this approach only accounts for the recall of true positive results and does not provide guarantees on the deviation of incorrect results. To address this limitation, we focus on an Error-Bounded ANN method, which ensures that the returned results are a $(1/δ)$-approximation of the true values. Our approach adopts a graph-based framework. To enable Error-Bounded ANN search, we propose a $δ$-EMG (Error-bounded Monotonic Graph), which, for the first time, provides a provable approximation for arbitrary queries. By enforcing a $δ$-monotonic geometric constraint during graph construction, $δ$-EMG ensures that any greedy search converges to a $(1/δ)$-approximate neighbor without backtracking. Building on this foundation, we design an error-bounded top-$k$ ANN search algorithm that adaptively controls approximation accuracy during query time. To make the framework practical at scale, we introduce $δ$-EMQG (Error-bounded Monotonic Quantized Graph), a localized and degree-balanced variant with near-linear construction complexity. We further integrate vector quantization to accelerate distance computation while preserving theoretical guarantees. Extensive experiments on the ANN-Benchmarks dataset demonstrate the effectiveness of our approach. Under a recall requirement of 0.99, our algorithm achieves 19,000 QPS on the SIFT1M dataset, outperforming other methods by more than 40\%.Open Accessδ-EMG: A Monotonic Graph Index for Approximate Nearest Neighbor Search
Approximate nearest neighbor (ANN) search in high-dimensional spaces is a foundational component of many modern retrieval and recommendation systems. Currently, almost all algorithms follow an $ε$-Recall-Bounded principle when comparing performance: they require the ANN search results to achieve a recall of more than $1-ε$ and then compare query-per-second (QPS) performance. However, this approach only accounts for the recall of true positive results and does not provide guarantees on the deviation of incorrect results. To address this limitation, we focus on an Error-Bounded ANN method, which ensures that the returned results are a $(1/δ)$-approximation of the true values. Our approach adopts a graph-based framework. To enable Error-Bounded ANN search, we propose a $δ$-EMG (Error-bounded Monotonic Graph), which, for the first time, provides a provable approximation for arbitrary queries. By enforcing a $δ$-monotonic geometric constraint during graph construction, $δ$-EMG ensures that any greedy search converges to a $(1/δ)$-approximate neighbor without backtracking. Building on this foundation, we design an error-bounded top-$k$ ANN search algorithm that adaptively controls approximation accuracy during query time. To make the framework practical at scale, we introduce $δ$-EMQG (Error-bounded Monotonic Quantized Graph), a localized and degree-balanced variant with near-linear construction complexity. We further integrate vector quantization to accelerate distance computation while preserving theoretical guarantees. Extensive experiments on the ANN-Benchmarks dataset demonstrate the effectiveness of our approach. Under a recall requirement of 0.99, our algorithm achieves 19,000 QPS on the SIFT1M dataset, outperforming other methods by more than 40\%. - Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (4) , 1-27
Scaling Up k-Clique Percolation Community Detection
Overlapping communities are pervasive in real-world networks, where vertices often participate in multiple communities simultaneously. The k -clique percolation community (KCPC) model represents a fundamental paradigm for mining overlapping communities. However, existing KCPC mining methods are often hampered by inefficiency and scalability challenges, hindering their applicability to large-scale networks. To address these challenges, we propose several novel and efficient approaches for KCPC mining from perspectives of maximal cliques and k -cliques. Specifically, we first present a novel concept, termed Quasi-KCPC, which represents an incomplete KCPC and can be efficiently obtained as a byproduct during the maximal clique enumeration procedure. Based on Quasi-KCPC, we first propose a maximal clique enumeration-based solution that builds upon existing maximal clique adjacency graph traversal methods, but achieves improved efficiency by using Quasi-KCPC to dramatically reduce the scale of the maximal clique adjacency graph. Additionally, we propose a novel k -clique listing-based solution, which adopts a different strategy: it first enumerates (k-1)-cliques and then connects the k -cliques sharing these (k-1)-cliques into KCPC. Our method further improves efficiency by shifting the connection target from k -cliques to maximal cliques and employing Quasi-KCPC to significantly prune the k -clique enumeration tree. We also propose update algorithms for KCPC to handle dynamic addition and deletion of vertices and edges, enabling real-time analysis of KCPC. Extensive experiments on 12 large real-world graphs demonstrate the superiority of our algorithms, which can be up to two orders of magnitude faster than existing state-of-the-art solutions in KCPC mining, and almost two orders of magnitude faster than recomputation strategy in dynamic KCPC updates.
- 22 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (4) , 1-27
Open AccessScaling Up k-Clique Percolation Community Detection
Overlapping communities are pervasive in real-world networks, where vertices often participate in multiple communities simultaneously. The k -clique percolation community (KCPC) model represents a fundamental paradigm for mining overlapping communities. However, existing KCPC mining methods are often hampered by inefficiency and scalability challenges, hindering their applicability to large-scale networks. To address these challenges, we propose several novel and efficient approaches for KCPC mining from perspectives of maximal cliques and k -cliques. Specifically, we first present a novel concept, termed Quasi-KCPC, which represents an incomplete KCPC and can be efficiently obtained as a byproduct during the maximal clique enumeration procedure. Based on Quasi-KCPC, we first propose a maximal clique enumeration-based solution that builds upon existing maximal clique adjacency graph traversal methods, but achieves improved efficiency by using Quasi-KCPC to dramatically reduce the scale of the maximal clique adjacency graph. Additionally, we propose a novel k -clique listing-based solution, which adopts a different strategy: it first enumerates (k-1)-cliques and then connects the k -cliques sharing these (k-1)-cliques into KCPC. Our method further improves efficiency by shifting the connection target from k -cliques to maximal cliques and employing Quasi-KCPC to significantly prune the k -clique enumeration tree. We also propose update algorithms for KCPC to handle dynamic addition and deletion of vertices and edges, enabling real-time analysis of KCPC. Extensive experiments on 12 large real-world graphs demonstrate the superiority of our algorithms, which can be up to two orders of magnitude faster than existing state-of-the-art solutions in KCPC mining, and almost two orders of magnitude faster than recomputation strategy in dynamic KCPC updates.
- 8 September 2025
- Published by Springer Nature in The VLDB Journal
- Vol. 34 (6) , 1-26
Density decomposition on large static and dynamic graphs: algorithms and applications
- 8 September 2025
- Published by Springer Nature in The VLDB Journal
- Vol. 34 (6) , 1-26
Density decomposition on large static and dynamic graphs: algorithms and applications