Author name cluster

Wu Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

JBHI Journal 2026 Journal Article

Precise Decision Energized Collaborative Strategies to Achieve High-Quality and Large-Scale Neuronal Reconstruction

Mingwei Liao
Wu Chen
Shengda Bao
Ganghua Huang
Hui Gong
Qingming Luo
Xiaowei Chen
Jiandong Zhou

The brain is the least explored organ in the human body. Brain functions are realized through a complex neural network composed of a vast number of neurons, and understanding the morphology of these neurons is base to brain studies. However, obtaining high-quality, large-scale data on neuron morphology remains a significant challenge. In this study, we propose a precise data-graded allocation method for neuron reconstruction, the accuracy is safeguarded by the allocation algorithm and the quantitative model. Reconstruction efficiency was improved by optimizing automated reconstruction algorithm, human-machine interaction workflow and human-task matching method. We have implemented this strategy on a web-based platform, and the results show that 92. 9% of image data can be easily reconstructed, thereby reducing the skill requirements for participant. The reconstruction accuracy is 98. 2% $\pm$ 3. 1%, better than existing methods. We also provides meticulously annotated datasets that can propel significant advancements in artificial intelligence technology. In addition, we can offer a well-balance across quality, cost, and efficiency, sharing a more flexible and versatile solution for three-dimensional neuron reconstruction.

Details DOI

AAMAS Conference 2026 Conference Paper

Safe Multi-Agent Reinforcement Learning Through Neural Graph Control Barrier Functions

Ziye Deng
Qiang Li
Mingyue Zhang
Wu Chen

Multi-Agent Reinforcement Learning (MARL) has shown great potentialinawiderangeofdomains, butitstrial-and-errorexploration paradigm can lead to severe risks in safety-critical tasks. Existing approaches to safe MARL, including reward shaping, constrained optimization, and shielding, provide only soft guarantees and are often insufficient to ensure strict safety. In contrast, Control Barrier Functions (CBFs) from control theory offer a principled way to enforce safety by keeping system states within a safe set at all times, providing new opportunities to address safety in reinforcement learning. In this work, we propose a novel framework that integrates CBFs with MARL to guarantee safety while preserving learning performance. Comprehensive evaluations in standard benchmark environments demonstrate that our method consistently achieves zero-violation safety constraints and matches or even surpasses existing methods in terms of performance.

PDF

AAAI Conference 2025 Conference Paper

Learning Verified Safe Neural Network Controllers for Multi-Agent Path Finding

Mingyue Zhang
Nianyu Li
Yi Chen
Jialong Li
Xiao-Yi Zhang
Hengjun Zhao
Jiamou Liu
Wu Chen

Multi-agent path finding (MAPF) is a safety-critical scenario where the goal is to secure collision-free trajectories from initial to desired locations. However, due to system complexity and uncertainty, integrating learning-based controllers with MAPF is challenging and cannot theoretically guarantee the safety of the learned controllers. In response, our study proposes a verified safe multi-agent neural control (VSMANC) approach for MAPF, focusing on the unified training of Decentralized Control Barrier Functions (DCBF) and controllers to enhence safety. VSMANC enables all agents to concurrently learn controllers and DCBFs using a unified loss function designed to maximize safety, adhere to standard control policies, and incorporate path-finding-related heuristics. We also propose a formal verification-guided retraining process to both verify the properties of the learned DCBFs and generate counterexamples for retraining, thereby providing a verified safety guarantee. We validate our approach through shape formation experiments and UAV simulations, demonstrating significant improvements in safety and effectiveness in complex multi-agent environments.

PDF Details DOI

AAMAS Conference 2025 Conference Paper

SFedRec: A Federated Learning Framework for Dynamic Session-based Recommendation

Hexiao Zhang
Yanni Tang
Jiamou Liu
Wu Chen

Session-based recommendation systems are critical for capturing users’ evolving interests in real-time interactions. However, applying such systems in a federated learning (FL) setting presents challenges related to decentralized data and privacy preservation. To address this, we propose SFedRec, a session-based federated recommendation framework that integrates long-term user preferences with dynamicd session-based behaviors. SFedRec builds decentralized heterogeneous knowledge graphs to model user-item interactions and social connections, utilizing a graph neural network to learn user representations while ensuring privacy through Local Differential Privacy (LDP). Extensive experiments on three real-world datasets demonstrate that SFedRec outperforms stateof-the-art federated recommendation models, showing significant improvements in both general and cold-start scenarios.

PDF

LOPSTR Conference 2014 Conference Paper

Polynomial Approximation to Well-Founded Semantics for Logic Programs with Generalized Atoms: Case Studies

Md. Solimul Chowdhury
Fangfang Liu 0008
Wu Chen
Arash Karimi
Jia-Huai You

Abstract The well-founded semantics of normal logic programs has two main utilities, one being an efficiently computable semantics with a unique intended model, and the other serving as polynomial time constraint propagation for the computation of answer sets of the same program. When logic programs are generalized to support constraints of various kinds, the semantics is no longer tractable, which makes the second utility doubtful. This paper considers the possibility of tractable but incomplete methods, which in general may miss information in the computed result, but never generates wrong conclusions. For this goal, we first formulate a well-founded semantics for logic programs with generalized atoms, which generalizes logic programs with arbitrary aggregates/constraints/dl-atoms. As a case study, we show that the method of removing non-monotone dl-atoms for the well-founded semantics by Eiter et al. actually falls into this category. We also present a case study for logic programs with standard aggregates.

Details