XFXiaolong Fan

Xiaolong Fan

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaolong Fan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Personalized Federated Contrastive Learning for Recommendation

    by Shanfeng Wang, Yuxi Zhou, Xiaolong Fan, Jianzhao Li, Zexuan Lei, Maoguo Gong

    Recommender systems play crucial roles in addressing the issue of information overload, but traditional centralized storage in recommendation poses significant privacy concerns. In recent years, federated learning has been successfully introduced into a recommendation, while these algorithms still encounter several challenges. First, real-world recommendation scenarios often suffer from sparse data, making it difficult for models to learn reliable representations. Second, data heterogeneity necessitates the design of personalized models to enhance recommendation performance. To address these challenges, we propose a federated recommendation approach based on graph neural networks, named federated personalized contrastive learning for recommendation. On the client side, we propose a contrastive learning approach to enhance the embedding quality of nodes (users or items) by maximizing positive similarities. Specifically, we formulate the concept of structural neighbors based on the graph structure and devise a contrastive learning objective. We treat nodes and their structural neighbors as positive pairs to better learn node representations. On the server side, we group users based on the learned representations and compute cluster-level federated models and a global model. Each user learns a personalized model by combining these two models. Extensive experiments on five real-world datasets demonstrate that the proposed algorithm outperforms existing methods in terms of performance.


  • CLMFN: An Intelligent Discrimination Method of Deception Jamming Based on Multimodal Systems

    by Yongkang Wang, Jieyi Liu, Maoguo Gong, Yu Zhou, Xiaolong Fan, Hao Li

    The existing anti-jamming methods are based on single modality, lacking cross-modalities feature extraction and general discriminant algorithms. In order to increase the diversity of the discriminant scenarios, a multi-modal fusion model of jamming countermeasure is proposed. The model can collaboratively process cross-modalities information and prevent the loss of discrimination performance when lacking partial modalities, thus ensuring the all-round utilization of information. Specifically, a convolutional neural network and an attention-based bidirectional long short-term memory network model are constructed to extract complex envelope features of signal modality and kinematic time-series features of data modality, respectively. At the same time, the two features are fused to learn joint representations between cross modalities. The constraint condition is added to the loss function which can ensure various feature vectors are highly correlated, so that the discrimination remains good even facing the single modality. Extensive experimental results show that the performance of proposed multi-modal network is superior to the single modal network. Specifically, the proposed model exhibits robustness for different modalities and can intelligently adjust the dependence on different modalities.


  • Learning Compact Transformation Based on Dual Quaternion for Point Cloud Registration

    by Yongzhe Yuan, Yue Wu, Jiayi Lei, Congying Hu, Maoguo Gong, Xiaolong Fan, Wenping Ma, Qiguang Miao

    Accurately estimating 3-D rigid body transformation is a critical step for correspondences-free point cloud registration method. However, recently proposed methods have faced challenges in effectively estimating rigid body transformation due to issues related to parameters redundancy and singularity. In this article, we propose a new framework to estimate rigid transformation by dual quaternion which provides a compact representation for rigid transformation information. Different from traditional methods which generate dual quaternion utilizing prior knowledge, the multiscale features association network (MFANet) is introduced to adaptively learn transformation parameters of dual quaternion for accurately estimating rigid transformation. In addition, MFANet enhances data interaction between feature maps of low-dimensional and high-dimensional, which can potentially promote the learning of transformation parameters and reduce the appearance of preference features. Finally, our method demonstrates superior precision and robustness through comprehensive experiments conducted on synthetic dataset ModelNet40 and real-world dataset 3DMatch.


  • Open Access

    Learning Data-Driven Propagation Mechanism for Graph Neural Network

    by Yue Wu, Xidao Hu, Xiaolong Fan, Wenping Ma, Qiuyue Gao

    A graph is a relational data structure suitable for representing non-Euclidean structured data. In recent years, graph neural networks (GNN) and their subsequent variants, which utilize deep neural networks to complete graph analysis and representation, have shown excellent performance in various application fields. However, the propagation mechanism of existing methods relies on hand-designed GNN layer connection architecture, which is prone to information redundancy and over-smoothing problems. To alleviate this problem, we propose a data-driven propagation mechanism to adaptively propagate information between layers. Specifically, we construct a bi-level optimization objective and use the gradient descent algorithm to learn the forward propagation architecture, which improves the efficiency of learning different layer combinations in multilayer networks. The experimental results of the model on seven benchmark datasets demonstrate the effectiveness of the proposed method. Furthermore, combining this data-driven propagation mechanism with models, such as Graph Attention Networks, can consistently improve the performance of these models.