ST-ProC：一种用于鲁棒半监督出行方式识别的图原型框架
ST-ProC: A Graph-Prototypical Framework for Robust Semi-Supervised Travel Mode Identification
AI总结：
针对GPS轨迹出行方式识别（TMI）的标签稀缺问题，提出ST-ProC图原型多目标半监督框架，结合图正则化、原型锚定及边缘感知伪标签策略，较FixMatch提升21.5%性能。
摘要：
GPS轨迹的出行方式识别（TMI）对城市智能至关重要，但标注成本高导致标签稀缺问题严重。主流半监督学习（SSL）方法因存在灾难性确认偏差且忽略数据内在流形，不适用于该任务。我们提出ST-ProC，一种新颖的图原型多目标SSL框架以解决这些局限。该框架将图原型核心与基础SSL支持相结合：核心通过图正则化、原型锚定及新的边缘感知伪标签策略利用数据流形，基础支持则通过对比损失和师生一致性损失确保高质量表示与鲁棒优化。ST-ProC显著优于所有基线，在真实稀疏标签场景中有效，较FixMatch等最先进方法性能提升21.5%。
英文摘要：
Travel mode identification (TMI) from GPS trajectories is critical for urban intelligence, but is hampered by the high cost of annotation, leading to severe label scarcity. Prevailing semi-supervised learning (SSL) methods are ill-suited for this task, as they suffer from catastrophic confirmation bias and ignore the intrinsic data manifold. We propose ST-ProC, a novel graph-prototypical multi-objective SSL framework to address these limitations. Our framework synergizes a graph-prototypical core with foundational SSL Support. The core exploits the data manifold via graph regularization, prototypical anchoring, and a novel, margin-aware pseudo-labeling strategy to actively reject noise. This core is supported and stabilized by foundational contrastive and teacher-student consistency losses, ensuring high-quality representations and robust optimization. ST-ProC outperforms all baselines by a significant margin, demonstrating its efficacy in real-world sparse-label settings, with a performance boost of 21.5% over state-of-the-art methods like FixMatch.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
