Junhong Wan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junhong Wan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Weihao Jiang
Hikvision Research Institute, Hangzhou, China
3 shared publications - Yao Fu
Hikvision Research Institute, Hangzhou, China
3 shared publications - Junlan Yu
Hikvision Research Institute, Hangzhou, China
2 shared publications - Shiliang Pu
Hikvision
2 shared publications - Jiang Zhu
Hikvision Research Institute, Hangzhou, China
1 shared publication - Ruiheng Yang
Hikvision Research Institute, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3942-3951
Decoder-only Pre-training Enhancement for Spatio-temporal Traffic Forecasting
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3942-3951
Open AccessDecoder-only Pre-training Enhancement for Spatio-temporal Traffic Forecasting
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 524-534
Cognitive-inspired Graph Redundancy Networks for Multi-source Information Fusion
The recent developments in technologies bring not only increasing amount of information but also multiple information sources for Graph Representation Learning. With the success of Graph Neural Networks (GNN), there have been increasing attempts to learn representation of multi-source information leveraging its graph structures. However, existing graph methods basically combine multi-source information with different contribution scores and over-simplify the graph structures based on prior knowledge, which fail to unify complex and conflicting multi-source information. Multisensory Processing theory in cognitive neuroscience reveals human mechanism of learning multi-source information by identifying the redundancy and complementarity. Inspired by that, we propose Graph Redundancy Network (GRN) that: 1). learns a suitable representation space that maximizes multi-source interactions; 2). encodes the redundant and complementary information according to Graph Intersection and Difference of their graph structures; 3). further reinforces and explores the redundant and complementary information through low-pass and high-pass graph filters. The empirical study shows that GRN outperforms existing methods on various tasks.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 524-534
Open AccessCognitive-inspired Graph Redundancy Networks for Multi-source Information Fusion
The recent developments in technologies bring not only increasing amount of information but also multiple information sources for Graph Representation Learning. With the success of Graph Neural Networks (GNN), there have been increasing attempts to learn representation of multi-source information leveraging its graph structures. However, existing graph methods basically combine multi-source information with different contribution scores and over-simplify the graph structures based on prior knowledge, which fail to unify complex and conflicting multi-source information. Multisensory Processing theory in cognitive neuroscience reveals human mechanism of learning multi-source information by identifying the redundancy and complementarity. Inspired by that, we propose Graph Redundancy Network (GRN) that: 1). learns a suitable representation space that maximizes multi-source interactions; 2). encodes the redundant and complementary information according to Graph Intersection and Difference of their graph structures; 3). further reinforces and explores the redundant and complementary information through low-pass and high-pass graph filters. The empirical study shows that GRN outperforms existing methods on various tasks.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2502-2511
GraphFADE: Field-aware Decorrelation Neural Network for Graphs with Tabular Features
Graph Neural Networks (GNNs) have achieved great success in recent years for their remarkable ability to extract effective representations from both node features and graph structures. Most of GNNs only focus on graphs with homogeneous features that correspond to one single feature field. For tabular features that are heterogeneous with multiple feature fields, GNNs often perform less favorably compared to machine learning methods such as boosted trees. In this work, we propose a new perspective to uncover the problem of GNNs on graphs with tabular features through both empirical study and theoretical analysis. The assumption of GNNs that connected nodes exhibit similar patterns can barely hold true for tabular features since multiple feature fields already exhibit different patterns. And propagation on such mismatched graph causes propagated features overcorrelated on graphs, which leads to the reduction of feature diversity and the increase of information redundancy. Therefore, we propose Field-aware Decorrelation Neural Network for graphs with tabular features (GraphFADE), a novel framework that directly optimizes the overcorrelation problem for graphs with tabular features. We first hierarchically partition the dataset into subsets with minimal correlation and then according to the decorrelation clustering results assemble the optimal matched graphs for each feature dimension to propagate on. The empirical study shows that our method achieves superior performance on multiple graphs with tabular features, demonstrating the effectiveness of our model.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2502-2511
Open AccessGraphFADE: Field-aware Decorrelation Neural Network for Graphs with Tabular Features
Graph Neural Networks (GNNs) have achieved great success in recent years for their remarkable ability to extract effective representations from both node features and graph structures. Most of GNNs only focus on graphs with homogeneous features that correspond to one single feature field. For tabular features that are heterogeneous with multiple feature fields, GNNs often perform less favorably compared to machine learning methods such as boosted trees. In this work, we propose a new perspective to uncover the problem of GNNs on graphs with tabular features through both empirical study and theoretical analysis. The assumption of GNNs that connected nodes exhibit similar patterns can barely hold true for tabular features since multiple feature fields already exhibit different patterns. And propagation on such mismatched graph causes propagated features overcorrelated on graphs, which leads to the reduction of feature diversity and the increase of information redundancy. Therefore, we propose Field-aware Decorrelation Neural Network for graphs with tabular features (GraphFADE), a novel framework that directly optimizes the overcorrelation problem for graphs with tabular features. We first hierarchically partition the dataset into subsets with minimal correlation and then according to the decorrelation clustering results assemble the optimal matched graphs for each feature dimension to propagate on. The empirical study shows that our method achieves superior performance on multiple graphs with tabular features, demonstrating the effectiveness of our model.