YWYong Wang

Yong 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


Yong Wang has a total of 85 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • API Recommendation for Novice Programmers: From Clear Expressions to Effective Results

    by Yong Wang, Shuai Meng, Yingtao Fang, Cuiyun Gao, Yourui Huang

    API recommendation systems for novice programmers should prioritize usability and inspiration rather than merely pursuing the “best result”. Existing retrieval-based approaches, whether relying on direct similarity matching or using query expansion to generate clarification options, still cannot recover missing task semantics and often introduce additional ambiguity and interaction overhead. Learning-based methods, including neural architectures and recent LLM-driven techniques, require substantial data or strong prompt dependence and provide limited transparency, making it difficult to align model outputs with novice programmers' actual intent. To address these limitations, we propose IOCAPI (Intention-Oriented and Context-Aware API Recommendation), a reasoning-driven framework that integrates LLMs, LCMs, and in-context learning. It mainly contains three components: (1) Intent Detector, which refines the query and derives task semantics through model-generated I/O exemplars; (2) Code Generator, which produces representative code snippets under the confirmed I/O constraints; and (3) Task Bridger, which consolidates the results into actionable API recommendations with interpretable code examples. Evaluations on three public datasets show that IOCAPI attains a 35.7% BLEU improvement over APIGen and an 11.1% MRR gain over CLEAR, and achieves higher MAP scores than GPT-4 zero-shot, few-shot, and chain-of-thought baselines by 102%, 11.2%, and 21.8%, respectively. A controlled user study involving seven real programming tasks further provides empirical observations of IOCAPI's behavior in practice. Compared with KAHAID, IOCAPI obtained higher average scores in Correctness (1.67 vs. 1.00), Usability (1.76 vs. 0.40), and Inspiration (1.40 vs. 0.26).


  • Open Access

    Auto-weighted Multi-view Subspace Clustering with Consistency Learning

    by Ao Li, Yong Wang, Lihao Yang, Shuai Meng

    Multi-view subspace clustering (MSC) has received widespread attention due to its ability to efficiently exploit consensus and diversity information from multiple perspectives. However, existing methods focus more on inter-view diversity and ignore the consistent associations and higher-order features among views under different perspectives. To solve the above problems, an auto-weighted MSC with consistency learning (AWMSCC) is proposed. Specifically, this method first integrates the shared features of all coefficient matrices in a three-factor decomposition to construct a new shared consistency matrix. Then, by using the tensor low-rank constraint, the coefficient matrices and the shared consistency matrix are stacked into a third-order tensor to achieve effective propagation of inter-view consistency information. Finally, the appropriate weights are adaptively assigned to all matrix information to obtain a high-quality affinity matrix. Experimental results on four benchmark datasets show that AWMSCC outperforms seven other advanced clustering algorithms in terms of performance.

  • Open Access

    Tensorized Multi-View Subspace Clustering via Tensor Nuclear Norm and Block Diagonal Representation

    by Gan-Yi Tang, Gui-Fu Lu, Yong Wang, Li-Li Fan

    Recently, a growing number of researchers have focused on multi-view subspace clustering (MSC) due to its potential for integrating heterogeneous data. However, current MSC methods remain challenged by limited robustness and insufficient exploitation of cross-view high-order latent information for clustering advancement. To address these challenges, we develop a novel MSC framework termed TMSC-TNNBDR, a tensorized MSC framework that leverages t-SVD based tensor nuclear norm (TNN) regularization and block diagonal representation (BDR) learning to unify view consistency and structural sparsity. Specifically, each subspace representation matrix is constrained by a block diagonal regularizer to enforce cluster structure, while all matrices are aggregated into a tensor to capture high-order interactions. To efficiently optimize the model, we developed an optimization algorithm based on the inexact augmented Lagrange multiplier (ALM). The TMSC-TNNBDR exhibits both optimized block-diagonal structure and low-rank properties, thereby enabling enhanced mining of latent higher-order inter-view correlations while demonstrating greater resilience to noise. To investigate the capability of TMSC-TNNBDR, we conducted several experiments on certain datasets. Benchmarking on circumscribed datasets demonstrates our method’s superior clustering performance over comparative algorithms while maintaining competitive computational overhead.

  • KanDMVC: KAN be used for deep multi-view clustering?

    by Yifan Zhang, Yong Wang, Guifu Lu, Cuiyun Gao, Lin Cui, Zizhuang Ma


  • Open Access

    Repository-Level Graph Representation Learning for Enhanced Security Patch Detection

    by Xin-Cheng Wen, Zirui Lin, Cuiyun Gao, Hongyu Zhang, Yong Wang, Qing Liao

    Software vendors often silently release security patches without providing sufficient advisories (e.g., Common Vulnerabilities and Exposures) or delayed updates via resources (e.g., National Vulnerability Database). Therefore, it has become crucial to detect these security patches to ensure secure software maintenance. However, existing methods face the following challenges: (1) They primarily focus on the information within the patches themselves, overlooking the complex dependencies in the repository. (2) Security patches typically involve multiple functions and files, increasing the difficulty in well learning the representations. To alleviate the above challenges, this paper proposes a Repository-level Security Patch Detection framework named RepoSPD, which comprises three key components: 1) a repository-level graph construction, RepoCPG, which represents software patches by merging pre-patch and post-patch source code at the repository level; 2) a structure-aware patch representation, which fuses the graph and sequence branch and aims at comprehending the relationship among multiple code changes; 3) progressive learning, which facilitates the model in balancing semantic and structural information. To evaluate RepoSPD, we employ two widely-used datasets in security patch detection: SPI-DB and PatchDB. We further extend these datasets to the repository level, incorporating a total of 20,238 and 28,781 versions of repository in C/C++ programming languages, respectively, denoted as SPI-DB* and PatchDB*. We compare RepoSPD with six existing security patch detection methods and five static tools. Our experimental results demonstrate that RepoSPD outperforms the state-of-the-art baseline, with improvements of 11.90%, and 3.10% in terms of accuracy on the two datasets, respectively.

  • Open Access

    Similarity Pattern Enhancement for API Recommended Methods via Graph Representation Learning

    by Yingtao Fang, Yong Wang, Cuiyun Gao, Linjun Chen, Yifan Zhang

    Developers often utilize application programming interfaces (API) to simplify their development tasks. API recommendation methods can automatically recommend the APIs that developers need to improve development quality and efficiency. Recent research combines collaborative filtering with graph neural networks for API recommendation. However, these approaches often face the problem of sub-optimal graph representation due to data sparsity. To address these issues, we propose an API recommendation method that enhances the raw data by fusing usage patterns in similar projects. Typically, similar projects share similar functional and structural features, including code modules with similar usage patterns, which include rich information such as invocation and structural details. Enhancing the raw data with this information can effectively alleviate the sparsity problem of the interaction matrix induced by the construction graph of the raw data. Specifically, our approach consists of matching similar items for each entry in the original dataset to form new classes. These new classes are then merged into code modules with similar usage patterns to augment the original dataset. Subsequently, the graph represents the learning model capturing the higher-order collaborative signals of the API calls in the augmented dataset and integrating the structural information of the items into the graph. To evaluate the effectiveness of our approach, we conducted experiments using data collected from large open source repositories. The experimental results show that the method is effective.