Haiwei Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haiwei Zhang has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Xiaojie Yuan
Nankai University
8 shared publications - Yanlong Wen
College of Computer Science, Nankai University, Tianjin, China
5 shared publications - Changli Nie
College of CS, TJ Key Lab of NDST, Nankai University, Tianjin, China
3 shared publications - Dongming Zhao
China Mobile Communication Group Tianjin Co., Ltd
3 shared publications - Qijie Bai
College of Computer Science Nankai University Tianjin China
3 shared publications Qijie Bai
2 shared publications
Latest Publications
- 9 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Ordered Fusion from Head to Tail in Imbalanced Node Classification
- 9 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Ordered Fusion from Head to Tail in Imbalanced Node Classification
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (4) , 1-26
Minimum Change≠ Best Cleaning: Parallel and Incremental Error Detection under Integrity Constraints
Erroneous data frequently arise in practical scenarios due to a variety of factors, severely degrading data quality and impeding downstream applications. A widely adopted strategy for error detection is to detect conflicts based on integrity constraints and identify the minimum number of errors, thereby ensuring that the remaining cells satisfy the constraints. However, the minimum change principle may not be applicable in practical scenarios, since errors can occur simultaneously or irregularly. Therefore, this study employs Bayesian statistics to identify erroneous attribute values in conflicting cells that violate inter-attribute dependencies, rather than simply relying on the minimum change principle. This approach ensures that our work neither misses multiple erroneous attribute values conflicting with each other nor mistakenly detects outliers without errors. Furthermore, to address the efficiency issues commonly encountered in constraint-based data cleaning methods, we design 1) parallel conflict detection and error determination methods with the guaranteed parallel scalability, and 2) efficient incremental error detection strategies that can also be executed in parallel with such guarantees. Experiments conducted on various datasets demonstrate the superiority of our error detection methods in terms of both effectiveness and efficiency.
- 22 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (4) , 1-26
Open AccessMinimum Change≠ Best Cleaning: Parallel and Incremental Error Detection under Integrity Constraints
Erroneous data frequently arise in practical scenarios due to a variety of factors, severely degrading data quality and impeding downstream applications. A widely adopted strategy for error detection is to detect conflicts based on integrity constraints and identify the minimum number of errors, thereby ensuring that the remaining cells satisfy the constraints. However, the minimum change principle may not be applicable in practical scenarios, since errors can occur simultaneously or irregularly. Therefore, this study employs Bayesian statistics to identify erroneous attribute values in conflicting cells that violate inter-attribute dependencies, rather than simply relying on the minimum change principle. This approach ensures that our work neither misses multiple erroneous attribute values conflicting with each other nor mistakenly detects outliers without errors. Furthermore, to address the efficiency issues commonly encountered in constraint-based data cleaning methods, we design 1) parallel conflict detection and error determination methods with the guaranteed parallel scalability, and 2) efficient incremental error detection strategies that can also be executed in parallel with such guarantees. Experiments conducted on various datasets demonstrate the superiority of our error detection methods in terms of both effectiveness and efficiency.
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 634-643
OpenSGen: Fine-Grained Relation-Aware Prompt for Open-Vocabulary Scene Graph Generation
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 634-643
Open AccessOpenSGen: Fine-Grained Relation-Aware Prompt for Open-Vocabulary Scene Graph Generation
- Open Access
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-27
The Best of Both Worlds: On Repairing Timestamps and Attribute Values for Multivariate Time Series
Dirty data are often observed in the multivariate time series, which not only degrades data quality but also adversely affects various downstream applications. Existing studies typically focus on repairing such errors appearing in either timestamps or attribute values alone, relying on the assumption that the other part is clean. However, in real scenarios, owing to various reasons, both timestamps and attribute values can be erroneous. It is intuitive to repair timestamps and attribute values respectively by calling different methods in turn. However, such a strategy may lead to over-repairing and introduce additional errors, by ignoring the mutual reference between timestamps and attribute values. Therefore, in this study, rather than repairing timestamps and attribute values respectively by calling different methods in turn, we consider the repairing for both attribute values and timestamps simultaneously. Our major contributions include (1) defining the multivariate speed constraints and formalizing the optimal repair problem with the NP-hardness analysis, (2) computing the exact solutions with pruning strategies and correctness ensurance, (3) designing the quadratic time approximation algorithm with the performance guarantee, (4) devising the linear time algorithm and ensuring its approximation performance bound. Empirical results over real-world dirty datasets demonstrate the superiority and practicality of our algorithms, against eleven competing methods, where our algorithm not only achieves the best accuracy but also spends the lowest time cost.
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-27
Open AccessThe Best of Both Worlds: On Repairing Timestamps and Attribute Values for Multivariate Time Series
Dirty data are often observed in the multivariate time series, which not only degrades data quality but also adversely affects various downstream applications. Existing studies typically focus on repairing such errors appearing in either timestamps or attribute values alone, relying on the assumption that the other part is clean. However, in real scenarios, owing to various reasons, both timestamps and attribute values can be erroneous. It is intuitive to repair timestamps and attribute values respectively by calling different methods in turn. However, such a strategy may lead to over-repairing and introduce additional errors, by ignoring the mutual reference between timestamps and attribute values. Therefore, in this study, rather than repairing timestamps and attribute values respectively by calling different methods in turn, we consider the repairing for both attribute values and timestamps simultaneously. Our major contributions include (1) defining the multivariate speed constraints and formalizing the optimal repair problem with the NP-hardness analysis, (2) computing the exact solutions with pruning strategies and correctness ensurance, (3) designing the quadratic time approximation algorithm with the performance guarantee, (4) devising the linear time algorithm and ensuring its approximation performance bound. Empirical results over real-world dirty datasets demonstrate the superiority and practicality of our algorithms, against eleven competing methods, where our algorithm not only achieves the best accuracy but also spends the lowest time cost.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 914-923
DHMAE: A Disentangled Hypergraph Masked Autoencoder for Group Recommendation
Group recommendation aims to suggest items to a group of users that are suitable for the group. Although some existing powerful deep learning models have achieved improved performance, various aspects remain unexplored: (1) Most existing models using contrastive learning tend to rely on high-quality data augmentation which requires precise contrastive view generation; (2) There is multifaceted natural noise in group recommendation, and additional noise is introduced during data augmentation; (3) Most existing hypergraph neural network-based models over-entangle the information of members and items, ignoring their unique characteristics. In light of this, we propose a highly effective Disentangled Hypergraph Masked Auto Encoder-enhanced method for group recommendation (DHMAE), combining a disentangled hypergraph neural network with a graph masked autoencoder. This approach creates self-supervised signals without data augmentation by masking the features of some nodes and hyperedges and then reconstructing them. For the noise problem, we design a masking strategy that relies on pre-computed degree-sensitive probabilities for the process of masking features. Furthermore, we propose a disentangled hypergraph neural network for group recommendation scenarios to extract common messages of members and items and disentangle them during the convolution process. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art models and effectively addresses the noise issue.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 914-923
Open AccessDHMAE: A Disentangled Hypergraph Masked Autoencoder for Group Recommendation
Group recommendation aims to suggest items to a group of users that are suitable for the group. Although some existing powerful deep learning models have achieved improved performance, various aspects remain unexplored: (1) Most existing models using contrastive learning tend to rely on high-quality data augmentation which requires precise contrastive view generation; (2) There is multifaceted natural noise in group recommendation, and additional noise is introduced during data augmentation; (3) Most existing hypergraph neural network-based models over-entangle the information of members and items, ignoring their unique characteristics. In light of this, we propose a highly effective Disentangled Hypergraph Masked Auto Encoder-enhanced method for group recommendation (DHMAE), combining a disentangled hypergraph neural network with a graph masked autoencoder. This approach creates self-supervised signals without data augmentation by masking the features of some nodes and hyperedges and then reconstructing them. For the noise problem, we design a masking strategy that relies on pre-computed degree-sensitive probabilities for the process of masking features. Furthermore, we propose a disentangled hypergraph neural network for group recommendation scenarios to extract common messages of members and items and disentangle them during the convolution process. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art models and effectively addresses the noise issue.
- 9 September 2023
- Published by Springer Nature
- p. 319-330
FocusCap: Object-Focused Image Captioning with CLIP-Guided Language Model
- 9 September 2023
- Published by Springer Nature
- p. 319-330
FocusCap: Object-Focused Image Captioning with CLIP-Guided Language Model
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 523-532
HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction
Temporal link prediction, aiming to predict future edges between paired nodes in a dynamic graph, is of vital importance in diverse applications. However, existing methods are mainly built upon uniform Euclidean space, which has been found to be conflict with the power-law distributions of real-world graphs and unable to represent the hierarchical connections between nodes effectively. With respect to the special data characteristic, hyperbolic geometry offers an ideal alternative due to its exponential expansion property. In this paper, we propose HGWaveNet, a novel hyperbolic graph neural network that fully exploits the fitness between hyperbolic spaces and data distributions for temporal link prediction. Specifically, we design two key modules to learn the spatial topological structures and temporal evolutionary information separately. On the one hand, a hyperbolic diffusion graph convolution (HDGC) module effectively aggregates information from a wider range of neighbors. On the other hand, the internal order of causal correlation between historical states is captured by hyperbolic dilated causal convolution (HDCC) modules. The whole model is built upon the hyperbolic spaces to preserve the hierarchical structural information in the entire data flow. To prove the superiority of HGWaveNet, extensive experiments are conducted on six real-world graph datasets and the results show a relative improvement by up to 6.67% on AUC for temporal link prediction over SOTA methods.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 523-532
Open AccessHGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction
Temporal link prediction, aiming to predict future edges between paired nodes in a dynamic graph, is of vital importance in diverse applications. However, existing methods are mainly built upon uniform Euclidean space, which has been found to be conflict with the power-law distributions of real-world graphs and unable to represent the hierarchical connections between nodes effectively. With respect to the special data characteristic, hyperbolic geometry offers an ideal alternative due to its exponential expansion property. In this paper, we propose HGWaveNet, a novel hyperbolic graph neural network that fully exploits the fitness between hyperbolic spaces and data distributions for temporal link prediction. Specifically, we design two key modules to learn the spatial topological structures and temporal evolutionary information separately. On the one hand, a hyperbolic diffusion graph convolution (HDGC) module effectively aggregates information from a wider range of neighbors. On the other hand, the internal order of causal correlation between historical states is captured by hyperbolic dilated causal convolution (HDCC) modules. The whole model is built upon the hyperbolic spaces to preserve the hierarchical structural information in the entire data flow. To prove the superiority of HGWaveNet, extensive experiments are conducted on six real-world graph datasets and the results show a relative improvement by up to 6.67% on AUC for temporal link prediction over SOTA methods.
- 14 April 2023
- Published by Springer Nature
- p. 556-567
Personalized Dissatisfied Users Prediction in Mobile Communication Service
- 14 April 2023
- Published by Springer Nature
- p. 556-567
Personalized Dissatisfied Users Prediction in Mobile Communication Service
- 8 December 2022
- Published by Springer Nature
- p. 473-484
Weighted Cost Model for Optimized Query Processing
- 8 December 2022
- Published by Springer Nature
- p. 473-484
Weighted Cost Model for Optimized Query Processing
- 8 December 2022
- Published by Springer Nature
- p. 254-266
Design and Implementation of Analyzer Management System Based on Elasticsearch
- 8 December 2022
- Published by Springer Nature
- p. 254-266
Design and Implementation of Analyzer Management System Based on Elasticsearch