WTWenjun Tang

Wenjun Tang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


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


Latest Publications

  • Open Access

    Type-Aware Heterogeneous Graph Network for Circuit Link Prediction

    by Meilin Li, Hui Li, Wenjun Tang, Qian Ma, Feng Min, Rubing Huang, He Jiang, Shikai Guo

    Link prediction for circuit completion is a crucial task in Electronic Design Automation (EDA), aiming to infer missing connections in incomplete circuits to accelerate design workflows and ensure Printed Circuit Board (PCB) reliability. However, due to the practical reality that circuit connectivity is defined by nets that connect specific pins of component instances, existing methods that rely on homogeneous representations and scalar shortest path distances collapse pin-level constraints into a single proximity signal. This collapse obscures component identities and pin semantics, and fails to capture long-range functional paths, which can slow design closure and potentially compromise PCB reliability by increasing the risk of electrically invalid links and subsequent rework. Addressing these challenges, we present a T ype-aware H eterogeneous G raph network for C ircuit link prediction ( THGC ), which enables accurate circuit link prediction by explicitly preserving component functional semantics and modeling type-aware dependencies. Specifically, THGC constructs a circuit-aware heterogeneous graph from netlists to preserve physical connectivity and component semantics, and refines representations through a multi-view encoder with Type-Aware Distance Encoding (TADE) to capture non-local dependencies. It then performs circuit-oriented link prediction using a heterogeneous graph network with dense convolutions and global sort pooling, optimized by a composite objective enforcing topological and semantic consistency, to predict electrically feasible missing connections for circuit completion. Comprehensive experiments are performed on 6,195 circuits collected from three benchmarks, and the results demonstrate that THGC consistently outperforms state-of-the-art methods, achieving up to a 47.51% relative improvement in terms of AUC. These results confirm that THGC effectively preserves component functional semantics and captures type-aware non-local dependencies for accurate circuit link prediction. The source code is available at https://anonymous.4open.science/r/THGC .

  • Open Access

    Architecture-Aware Multi-Scale Modeling with Self- and Cross-Attention for Dynamic IR Drop Analysis

    by Xianjing Zhu, Shikai Guo, Sihang Zhang, Wenjun Tang, Feng Min, Furui Zhan, Qian Ma, Ning Wang, Hui Li, He Jiang

    With the continued advancement of Very Large-Scale Integration (VLSI) technology, IR drop in Power Delivery Networks (PDNs) poses a serious threat to chip performance and reliability. Due to the complex cross-scale interactions between local hotspots and global power paths in real-world scenarios, existing approaches face the challenges of lacking a coupled representation of multi-scale features and ignoring long-range dependencies and spatiotemporal feature fusion. This severely limits the ability of IR drop prediction approaches to capture voltage-drop hotspots, undermining the accuracy and reliability of their predictions. Therefore, this paper proposes a novel prediction framework named IR-Hunter. IR-Hunter first employs heterogeneous convolution kernels to model local electrothermal hotspots and global PDN impedance distributions, precisely capturing hotspot locations and macro-scale current-flow paths critical for chip layout and routing. Then, it adaptively fuses these multi-scale features. Additionally, IR-Hunter learns global power interactions within the PDN to identify long-range voltage coupling effects affecting routing and power-grid stability. Finally, IR-Hunter leverages cross-metal-layer current propagation pathways, efficiently integrating cross-scale spatiotemporal information between the encoder and decoder stages, consistently improving IR drop prediction accuracy during chip design. Comprehensive experiments conducted on 20,578 samples collected from over 20K instances demonstrate IR-Hunter’s superior prediction accuracy, achieving an average 4.57% NRMSE reduction and 4.12% SSIM improvement compared to state-of-the-art approaches. Additionally, to foster advancements in the EDA community, we have open-sourced the code at https://github.com/xhhlzy/IR-Hunter.

  • Incentivizing Crowdsourcing Workers via Social Networks in Edge Computing

    by Wenjun Tang, Rong Chen, Zhikang Zhang, Shikai Guo

    Crowdsourcing has proven to be an effective approach for leveraging collective intelligence to solve tasks. However, in edge computing environments, crowdsourcing platforms often face challenges such as insufficient worker participation and weak collaboration. Existing incentive mechanisms focus on individual contributions, which leads to inefficient collaboration and suboptimal resource utilization, particularly on resource-constrained edge devices. Furthermore, limited computational capacity and budget constraints hinder widespread participation, negatively impacting task performance and overall engagement. This paper introduces the Agent Cooperation Model, which enhances worker collaboration and task completion through a distributed, agent-based approach to task allocation. We also propose the Deep Reinforcement Learning-based Dynamic Worker Incentive Mechanism (DDWM) to optimize incentive distribution using social network data, ensuring more effective incentives and fostering greater participation and collaboration. Cooperation Optimization through Multi-Agent Reinforcement Learning (MARL), allowing ACM to dynamically improve resource allocation and cooperation efficiency. The expansion of high-influence worker incentives through DDWM, driving broader participation via social networks. Experiments conducted on real-world datasets confirm that ACM and DDWM consistently enhance worker collaboration and participation across diverse and complex social networks. Compared to other incentive methods, these models exhibit superior stability and convergence, particularly in larger and denser networks, validating the effectiveness of our approach in fostering efficient crowdsourcing cooperation.