Dan Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dan Wu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Libing Wu
Wuhan University
4 shared publications - Imran Shafiq Ahmad
University of Windsor
2 shared publications - Rui Zhang
School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
2 shared publications - Shuqin Cao
School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China
2 shared publications - Amin Baghbanzadeh
School of Computer Science, University of Windsor, Windsor, Ontario, Canada
1 shared publication - Eric Neufeld
Department of Computer Science, University of Saskatchewan, Saskatoon, Saskatchewan, Canada
1 shared publication
Latest Publications
- Open Access
- 5 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 182-187
Resume-Job Compatibility Scoring Using Graph Neural Networks and Large Language Models
- 5 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 182-187
Open AccessResume-Job Compatibility Scoring Using Graph Neural Networks and Large Language Models
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 22 (2) , 1760-1774
Hypergraph Attention Recurrent Network for Cellular Traffic Prediction
Cellular traffic prediction provides significant support for the management of intelligent networks. Existing models commonly combine recurrent neural networks (RNNs) with attention mechanisms, convolutional neural networks (CNNs), or graph convolutional networks (GCNs) to capture spatial-temporal correlations of cellular traffic. However, attention mechanisms lack sensitivity to local information; CNNs ignore the interaction among distant regions with similar semantics; GCNs exhibit limitations in exploring high-order (beyond pairwise) spatial correlations. To this end, we develop a hypergraph attention recurrent network (HARN) that exploits locality, semantics, and high-order correlations for cellular traffic prediction. Specifically, we first propose a spatial trend-aware attention to perceive local trends, thus easing the mismatching problem of attention mechanisms. Then, we construct a hypergraph to characterize the interactions between distant regions with similar semantics, and leverage a hypergraph convolution network to extract high-order correlations. More importantly, to extract heterogeneous and varying spatial patterns, we further enhance the hypergraph convolution network by incorporating spatial-temporal representations. Last, extensive experiments on three real-world datasets demonstrate the superiority of HARN over state-of-the-art baselines in terms of mean absolute error and root mean square error, with specific improvements of 1.83% and 5.79% on SMS (short message service) dataset, 3.05% and 11.27% on Call dataset, and 1.36% and 1.65% on Internet dataset, respectively.
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 22 (2) , 1760-1774
Hypergraph Attention Recurrent Network for Cellular Traffic Prediction
Cellular traffic prediction provides significant support for the management of intelligent networks. Existing models commonly combine recurrent neural networks (RNNs) with attention mechanisms, convolutional neural networks (CNNs), or graph convolutional networks (GCNs) to capture spatial-temporal correlations of cellular traffic. However, attention mechanisms lack sensitivity to local information; CNNs ignore the interaction among distant regions with similar semantics; GCNs exhibit limitations in exploring high-order (beyond pairwise) spatial correlations. To this end, we develop a hypergraph attention recurrent network (HARN) that exploits locality, semantics, and high-order correlations for cellular traffic prediction. Specifically, we first propose a spatial trend-aware attention to perceive local trends, thus easing the mismatching problem of attention mechanisms. Then, we construct a hypergraph to characterize the interactions between distant regions with similar semantics, and leverage a hypergraph convolution network to extract high-order correlations. More importantly, to extract heterogeneous and varying spatial patterns, we further enhance the hypergraph convolution network by incorporating spatial-temporal representations. Last, extensive experiments on three real-world datasets demonstrate the superiority of HARN over state-of-the-art baselines in terms of mean absolute error and root mean square error, with specific improvements of 1.83% and 5.79% on SMS (short message service) dataset, 3.05% and 11.27% on Call dataset, and 1.36% and 1.65% on Internet dataset, respectively.
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (8) , 8705-8718
A Spatiotemporal Multiscale Graph Convolutional Network for Traffic Flow Prediction
Traffic prediction is vital to traffic planning, control, and optimization, which is necessary for intelligent traffic management. Existing methods mostly capture spatiotemporal correlations on a fine-grained traffic graph, which cannot make full use of cluster information in coarse-grained traffic graph. However, the flow variation of clusters in the coarse-grained traffic graph is more stable compared with nodes in the fine-grained traffic graph. And the flow variation of a fine-grained node is generally consistent with the trend of the cluster to which the node belongs. Thus information in the coarse-grained traffic graph can guide feature learning in the fine-grained traffic graph. To this end, we propose a Spatiotemporal Multiscale Graph Convolutional Network (SMGCN) that explores spatiotemporal correlations on a multiscale graph. Specifically, given a fine-grained traffic graph, we first generate a coarse-grained traffic graph by graph clustering, and extract spatiotemporal correlations on both fine-grained and coarse-grained traffic graphs. Then we propose a cross-scale fusion (CF) to implement information diffusion between the fine-grained and coarse-grained traffic graphs. Moreover, we employ an adaptive dynamic graph convolution network to mine both static and dynamic spatial features. We evaluate SMGCN on real-world datasets and obtain a $1.18\% -3.32\%$ improvement over state-of-the-arts.
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (8) , 8705-8718
A Spatiotemporal Multiscale Graph Convolutional Network for Traffic Flow Prediction
Traffic prediction is vital to traffic planning, control, and optimization, which is necessary for intelligent traffic management. Existing methods mostly capture spatiotemporal correlations on a fine-grained traffic graph, which cannot make full use of cluster information in coarse-grained traffic graph. However, the flow variation of clusters in the coarse-grained traffic graph is more stable compared with nodes in the fine-grained traffic graph. And the flow variation of a fine-grained node is generally consistent with the trend of the cluster to which the node belongs. Thus information in the coarse-grained traffic graph can guide feature learning in the fine-grained traffic graph. To this end, we propose a Spatiotemporal Multiscale Graph Convolutional Network (SMGCN) that explores spatiotemporal correlations on a multiscale graph. Specifically, given a fine-grained traffic graph, we first generate a coarse-grained traffic graph by graph clustering, and extract spatiotemporal correlations on both fine-grained and coarse-grained traffic graphs. Then we propose a cross-scale fusion (CF) to implement information diffusion between the fine-grained and coarse-grained traffic graphs. Moreover, we employ an adaptive dynamic graph convolution network to mine both static and dynamic spatial features. We evaluate SMGCN on real-world datasets and obtain a $1.18\% -3.32\%$ improvement over state-of-the-arts.
- Open Access
- 24 February 2023
- Published by MDPI AG in Information
- Vol. 14 (3) , 148
Multi-Dimensional Information Alignment in Different Modalities for Generalized Zero-Shot and Few-Shot Learning
Generalized zero-shot learning (GZSL) aims to solve the category recognition tasks for unseen categories under the setting that training samples only contain seen classes while unseen classes are not available. This research is vital as there are always existing new categories and large amounts of unlabeled data in realistic scenarios. Previous work for GZSL usually maps the visual information of the visible classes and the semantic description of the invisible classes into the identical embedding space to bridge the gap between the disjointed visible and invisible classes, while ignoring the intrinsic features of visual images, which are sufficiently discriminative to classify themselves. To better use discriminative information from visual classes for GZSL, we propose the n-CADA-VAE. In our approach, we map the visual feature of seen classes to a high-dimensional distribution while mapping the semantic description of unseen classes to a low-dimensional distribution under the same latent embedding space, thus projecting information of different modalities to corresponding space positions more accurately. We conducted extensive experiments on four benchmark datasets (CUB, SUN, AWA1, and AWA2). The results show our model’s superior performance in generalized zero-shot as well as few-shot learning.
- 24 February 2023
- Published by MDPI AG in Information
- Vol. 14 (3) , 148
Open AccessMulti-Dimensional Information Alignment in Different Modalities for Generalized Zero-Shot and Few-Shot Learning
Generalized zero-shot learning (GZSL) aims to solve the category recognition tasks for unseen categories under the setting that training samples only contain seen classes while unseen classes are not available. This research is vital as there are always existing new categories and large amounts of unlabeled data in realistic scenarios. Previous work for GZSL usually maps the visual information of the visible classes and the semantic description of the invisible classes into the identical embedding space to bridge the gap between the disjointed visible and invisible classes, while ignoring the intrinsic features of visual images, which are sufficiently discriminative to classify themselves. To better use discriminative information from visual classes for GZSL, we propose the n-CADA-VAE. In our approach, we map the visual feature of seen classes to a high-dimensional distribution while mapping the semantic description of unseen classes to a low-dimensional distribution under the same latent embedding space, thus projecting information of different modalities to corresponding space positions more accurately. We conducted extensive experiments on four benchmark datasets (CUB, SUN, AWA1, and AWA2). The results show our model’s superior performance in generalized zero-shot as well as few-shot learning.
- 27 June 2022
- Published by Springer Nature in World Wide Web
- Vol. 26 (1) , 115-137
Glider: rethinking congestion control with deep reinforcement learning
- 27 June 2022
- Published by Springer Nature in World Wide Web
- Vol. 26 (1) , 115-137
Glider: rethinking congestion control with deep reinforcement learning
- 6 June 2022
- Published by Springer Nature
- p. 99-115
Emergency Evacuation Software Simulation Process for Physical Changes
- 6 June 2022
- Published by Springer Nature
- p. 99-115
Emergency Evacuation Software Simulation Process for Physical Changes
- Open Access
- 1 January 2013
- Published by Springer Nature
- p. 25-42
A Generalized Neural Network Approach to Mobile Robot Navigation and Obstacle Avoidance
- 1 January 2013
- Published by Springer Nature
- p. 25-42
Open AccessA Generalized Neural Network Approach to Mobile Robot Navigation and Obstacle Avoidance
- 30 November 2009
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 50 (9) , 1331-1332
Special Track on Uncertain Reasoning of the 19th International Florida Artificial Intelligence Research Symposium (FLAIRS 2006)
- 30 November 2009
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 50 (9) , 1331-1332
Special Track on Uncertain Reasoning of the 19th International Florida Artificial Intelligence Research Symposium (FLAIRS 2006)
- 1 October 2007
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 46 (2) , 334-345
Maximal prime subgraph decomposition of Bayesian networks: A relational database perspective
- 1 October 2007
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 46 (2) , 334-345
Maximal prime subgraph decomposition of Bayesian networks: A relational database perspective
- 20 July 2004
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 19 (8) , 769-786
The marginal factorization of Bayesian networks and its application
- 20 July 2004
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 19 (8) , 769-786
The marginal factorization of Bayesian networks and its application