Xiaofeng Meng
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
Xiaofeng Meng has a total of 147 co-authors. Here are the top co-authors by number of shared publications:
- Jidong Chen
Department of Linguistics, California State University, Fresno, CA 93740, USA
13 shared publications - Aishan Maoliniyazi
Renmin University of China
6 shared publications - Tangpeng Dan
School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China
6 shared publications - Haibo Hu
The Hong Kong Polytechnic University, Hong Kong, China
5 shared publications - Leixia Wang
Northeastern University, Shenyang, Liaoning, China
5 shared publications - Qingqing Ye
The Hong Kong Polytechnic University, Hong Kong, China
5 shared publications
Latest Publications
- 23 October 2026
- Published by Springer Nature in The VLDB Journal
- Vol. 35 (6) , 63
Intra-query runtime elasticity
- 23 October 2026
- Published by Springer Nature in The VLDB Journal
- Vol. 35 (6) , 63
Intra-query runtime elasticity
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5790-5799
Efficient Privacy Auditing for Generative Model via Local Information
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5790-5799
Open AccessEfficient Privacy Auditing for Generative Model via Local Information
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2168-2179
Towards Robust Travel Time Estimation: An Out-of-Distribution Generalization Approach
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2168-2179
Open AccessTowards Robust Travel Time Estimation: An Out-of-Distribution Generalization Approach
- 3 August 2026
- Published by Springer Nature
- p. 280-295
As-ECTS: Adaptive Shapelet Learning for Early Classification of Streaming Time Series
- 3 August 2026
- Published by Springer Nature
- p. 280-295
As-ECTS: Adaptive Shapelet Learning for Early Classification of Streaming Time Series
- Open Access
- 11 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-32
DRAR: Diffusion-Based Relation Augmentation for Knowledge-aware Recommendation
Graph neural network-based recommenders employ the aggregation paradigms to learn node representation from higher-order neighboring nodes within the graph. However, these simple aggregation paradigms may perform poorly when mitigating noise impacts and capturing complex user preferences. To address it, some studies have attempted to enhance representation through contrastive augmentation across different views. Despite some effectiveness, the simple-view contrasts are still suboptimal with some unresolved challenges: (1) the influence of multivariate noise in interaction data, (2) knowledge biases introduced by irrelevant connections, and (3) user’s multiple interests. In this work, we propose a novel method named Diffusion-Based Relation Augmentation for Knowledge-aware Recommendation (DRAR) to overcome the above challenges. First, we alleviate the impact of interaction noise by injecting uncertainty and generating preference distributions with a diffusion-based module. Next, we design a relation augmentation module to effectively capture user neighborhood-level and context-level enhanced representations to alleviate the knowledge bias of irrelevant connections. Furthermore, we design a collaborative alignment module that enhances the model’s robustness by aligning user representation views at different stages. Extensive experiments on three benchmark datasets consistently demonstrate the superiority of our model over the state-of-the-art approaches. Our model demonstrates average improvements of 6.78% in Recall and 7.38% in NDCG across all datasets.
- 11 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-32
Open AccessDRAR: Diffusion-Based Relation Augmentation for Knowledge-aware Recommendation
Graph neural network-based recommenders employ the aggregation paradigms to learn node representation from higher-order neighboring nodes within the graph. However, these simple aggregation paradigms may perform poorly when mitigating noise impacts and capturing complex user preferences. To address it, some studies have attempted to enhance representation through contrastive augmentation across different views. Despite some effectiveness, the simple-view contrasts are still suboptimal with some unresolved challenges: (1) the influence of multivariate noise in interaction data, (2) knowledge biases introduced by irrelevant connections, and (3) user’s multiple interests. In this work, we propose a novel method named Diffusion-Based Relation Augmentation for Knowledge-aware Recommendation (DRAR) to overcome the above challenges. First, we alleviate the impact of interaction noise by injecting uncertainty and generating preference distributions with a diffusion-based module. Next, we design a relation augmentation module to effectively capture user neighborhood-level and context-level enhanced representations to alleviate the knowledge bias of irrelevant connections. Furthermore, we design a collaborative alignment module that enhances the model’s robustness by aligning user representation views at different stages. Extensive experiments on three benchmark datasets consistently demonstrate the superiority of our model over the state-of-the-art approaches. Our model demonstrates average improvements of 6.78% in Recall and 7.38% in NDCG across all datasets.
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (5) , 3182-3195
SUGPT: Efficient Graph Unsummarization for the Right to Be Forgotten
Graph data has become increasingly important in the AI and Big Data era. However, graph data analysis raises privacy concerns since it often originates from individual users. As a privacy regulation, the right to be forgotten has been established to allow users to erase their data hosted by a third party. When users request to delete their information from the original graph, the deletion must be synchronized to analysis results, like graph statistics or pre-trained AI models. In existing works, much effort has been made to fulfill the right to be forgotten for complicated graph learning models. In this work, we aim at a fundamental query — graph summarization, which serves as a building block for many graph analysis tasks. Since in summarization, when data removal requests are received, re-summarizing the graph from scratch can be costly, we present a novel approach to graph summarization regarding potential deletion requests. Inspired by machine unlearning, we define this problem as graph unsummarization which has three goals: efficiency, forgetting quality, and utility. Towards these goals, we propose SUGPT, a graph summarization and unsummarization method based on matrix partition and trie. The essence of SUGPT is to identify similarities between vertices by embedding matrix partitions into a trie structure, to accelerate summary updating upon deletion requests. We prove the forgetting quality of SUGPT theoretically and our extensive experiments demonstrate that SUGPT balances well in efficiency and utility in graph analysis.
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (5) , 3182-3195
SUGPT: Efficient Graph Unsummarization for the Right to Be Forgotten
Graph data has become increasingly important in the AI and Big Data era. However, graph data analysis raises privacy concerns since it often originates from individual users. As a privacy regulation, the right to be forgotten has been established to allow users to erase their data hosted by a third party. When users request to delete their information from the original graph, the deletion must be synchronized to analysis results, like graph statistics or pre-trained AI models. In existing works, much effort has been made to fulfill the right to be forgotten for complicated graph learning models. In this work, we aim at a fundamental query — graph summarization, which serves as a building block for many graph analysis tasks. Since in summarization, when data removal requests are received, re-summarizing the graph from scratch can be costly, we present a novel approach to graph summarization regarding potential deletion requests. Inspired by machine unlearning, we define this problem as graph unsummarization which has three goals: efficiency, forgetting quality, and utility. Towards these goals, we propose SUGPT, a graph summarization and unsummarization method based on matrix partition and trie. The essence of SUGPT is to identify similarities between vertices by embedding matrix partitions into a trie structure, to accelerate summary updating upon deletion requests. We prove the forgetting quality of SUGPT theoretically and our extensive experiments demonstrate that SUGPT balances well in efficiency and utility in graph analysis.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (4) , 2150-2164
Answering Range Queries for Arbitrary Distribution Under Shuffled Differential Privacy
Accurately answering range queries while protecting user privacy is critical in large-scale data collection scenarios. Current solutions for this problem based on local or shuffled differential privacy often use hierarchical trees, grids, and matrix mechanisms, which rely on domain decomposition and assume uniform distribution within sub-domains, resulting in significant accumulated noise errors and non-uniform errors when encountering non-uniform data distributions. To solve this problem, we propose a data distribution-aware structure in the shuffle model of differential privacy, called PriPL-Tree*. This structure uses a piecewise linear function to fit the data, eliminate non-uniform errors, and reduce noise, thanks to its concise tree structure and privacy amplification from shuffling. To build this tree with a balance of privacy, accuracy, and efficiency, we devise a novel node frequency estimation protocol for enhanced privacy amplification, a numerically optimized tree construction method for efficiency, and a weighted tree optimization method for improved accuracy. Additionally, we combine PriPL-Tree* with grids to adapt to multi-dimensional scenarios with optimally and non-uniformly allocated privacy budgets among dimensions. Through rigorous theoretical analysis and extensive experiments, we demonstrate the effectiveness and efficiency of our methods.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (4) , 2150-2164
Answering Range Queries for Arbitrary Distribution Under Shuffled Differential Privacy
Accurately answering range queries while protecting user privacy is critical in large-scale data collection scenarios. Current solutions for this problem based on local or shuffled differential privacy often use hierarchical trees, grids, and matrix mechanisms, which rely on domain decomposition and assume uniform distribution within sub-domains, resulting in significant accumulated noise errors and non-uniform errors when encountering non-uniform data distributions. To solve this problem, we propose a data distribution-aware structure in the shuffle model of differential privacy, called PriPL-Tree*. This structure uses a piecewise linear function to fit the data, eliminate non-uniform errors, and reduce noise, thanks to its concise tree structure and privacy amplification from shuffling. To build this tree with a balance of privacy, accuracy, and efficiency, we devise a novel node frequency estimation protocol for enhanced privacy amplification, a numerically optimized tree construction method for efficiency, and a weighted tree optimization method for improved accuracy. Additionally, we combine PriPL-Tree* with grids to adapt to multi-dimensional scenarios with optimally and non-uniformly allocated privacy budgets among dimensions. Through rigorous theoretical analysis and extensive experiments, we demonstrate the effectiveness and efficiency of our methods.
- 23 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 333
APKGC: An adaptive and prompt-tuning framework for knowledge graph completion
- 23 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 333
APKGC: An adaptive and prompt-tuning framework for knowledge graph completion
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3635-3644
KV-Auditor: Auditing Local Differential Privacy for Correlated Key-Value Estimation
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3635-3644
Open AccessKV-Auditor: Auditing Local Differential Privacy for Correlated Key-Value Estimation
- 17 October 2025
- Published by Springer Nature
- p. 3-18
Mender: Multi-dimensional Time Series Data Cleaning Based on Dynamic Patterns
- 17 October 2025
- Published by Springer Nature
- p. 3-18
Mender: Multi-dimensional Time Series Data Cleaning Based on Dynamic Patterns