SWShuhai Wang

Shuhai Wang

*This is an algorithmically generated author record based on publicly available information.

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


Shuhai Wang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Research on improved YOLOv5-based defect detection algorithm for cigarette air thinning head

    by Shuhai Wang, Ruihong Li, Ming Han, Zhijun Xu

    Cigarette empty thin head defect detection is an important step to ensure product quality in tobacco factories. To address the current problems about detecting thin head with little content and low accuracy, a cigarette empty thin head defect detection algorithm based on improved YOLOv5s is proposed. Firstly, a convolutional block attention mechanism is introduced between neck and head to emphasize the extraction of empty thin head defect features; then a weighted bidirectional feature pyramid structure is used to improve the neck network and enhance the feature fusion capability of the model; finally, a lightweight module is designed to reduce the computational complexity of the model. The experimental results show that the improved algorithm can effectively detect cigarette hollow-head defects with an improved accuracy of 2.1%, and the model parameters are only 5.35M, which can provide technical support for subsequent cigarette hollow-head defect detection.

  • Open Access

    Heterogeneous Graph Transformer for Meta-structure Learning with Application in Text Classification

    by Shuhai Wang, Xin Liu, Xiao Pan, Hanjie Xu, Mingrui Liu

    The prevalent heterogeneous Graph Neural Network (GNN) models learn node and graph representations using pre-defined meta-paths or only automatically discovering meta-paths. However, the existing methods suffer from information loss due to neglecting undiscovered meta-structures with richer semantics than meta-paths in heterogeneous graphs. To take advantage of the current rich meta-structures in heterogeneous graphs, we propose a novel approach called HeGTM to automatically extract essential meta-structures (i.e., meta-paths and meta-graphs) from heterogeneous graphs. The discovered meta-structures can capture more prosperous relations between different types of nodes that can help the model to learn representations. Furthermore, we apply the proposed approach for text classification. Specifically, we first design a heterogeneous graph for the text corpus, and then apply HeGTM on the constructed text graph to learn better text representations that contain various semantic relations. In addition, our approach can also be used as a strong meta-structure extractor for other GNN models. In other words, the auto-discovered meta-structures can replace the pre-defined meta-paths. The experimental results on text classification demonstrate the effectiveness of our approach to automatically extracting informative meta-structures from heterogeneous graphs and its usefulness in acting as a meta-structure extractor for boosting other GNN models.


  • Open Access

    GroupAligner : A Deep Reinforcement Learning with Domain Adaptation for Social Group Alignment

    by Li Sun, Yang Du, Shuai Gao, Junda Ye, Feiyang Wang, Fuxin Ren, Mingchen Liang, Yue Wang, Shuhai Wang

    Social network alignment, which aims to uncover the correspondence across different social networks, shows fundamental importance in a wide spectrum of applications such as cross-domain recommendation and information propagation. In the literature, the vast majority of the existing studies focus on the social network alignment at user level. In practice, the user-level alignment usually relies on abundant personal information and high-quality supervision, which is expensive and even impossible in the real-world scenario. Alternatively, we propose to study the problem of social group alignment across different social networks, focusing on the interests of social groups rather than personal information. However, social group alignment is non-trivial and faces significant challenges in both (i) feature inconsistency across different social networks and (ii) group discovery within a social network. To bridge this gap, we present a novel GroupAligner , a deep reinforcement learning with domain adaptation for social group alignment. In GroupAligner , to address the first issue, we propose the cycle domain adaptation approach with the Wasserstein distance to transfer the knowledge from the source social network, aligning the feature space of social networks in the distribution level. To address the second issue, we model the group discovery as a sequential decision process with reinforcement learning in which the policy is parameterized by a proposed p roximity-enhanced G raph N eural N etwork (pGNN) and a GNN-based discriminator to score the reward. Finally, we utilize pre-training and teacher forcing to stabilize the learning process of GroupAligner . Extensive experiments on several real-world datasets are conducted to evaluate GroupAligner , and experimental results show that GroupAligner outperforms the alternative methods for social group alignment.