用指令微调的Llama-3-8B模型，实现城市级长期出行预测。
Llama-Mob: Instruction-Tuning Llama-3-8B Excels in City-Scale Mobility Prediction
- 通过问答形式指令微调，建模长期出行轨迹。
- 在四个日本大都市数据上，15天预测优于现有方法。
- 仅用单城少量数据即可跨城泛化，适合城市规划者。
人类出行预测在灾害响应、城市规划和疫情预测中至关重要。传统方法依赖手工设计的领域特定模型，且多聚焦短期预测，难以在不同城市间泛化。本研究提出基于指令微调的Llama-3-8B-Mob模型，以问答形式进行长期城市级出行预测。我们在日本四个大都市的海量出行数据上验证该方法，目标是预测个体未来15天的移动轨迹。结果表明，Llama3-8B-Mob在多个评估指标上超越现有最先进方法，展现出强大的零样本泛化能力——即使仅在单一城市的少量数据上微调，也能有效推广到其他城市。此外，该方法具有通用性，可轻松扩展至下一流动兴趣点（POI）预测任务。为简洁起见，本文称该模型为Llama-Mob，相关结果均包含在内。源代码已公开于https://github.com/TANGHULU6/Llama3-8B-Mob。
原文摘要 · Abstract (English)
Human mobility prediction plays a critical role in applications such as disaster response, urban planning, and epidemic forecasting. Traditional methods often rely on designing crafted, domain-specific models, and typically focus on short-term predictions, which struggle to generalize across diverse urban environments. In this study, we introduce Llama3-8B-Mob, a large language model fine-tuned with instruction tuning, for long-term citywide mobility prediction--in a Q&A manner. We validate our approach using large-scale human mobility data from four metropolitan areas in Japan, focusing on predicting individual trajectories over the next 15 days. The results demonstrate that Llama3-8B-Mob excels in modeling long-term human mobility--surpassing the state-of-the-art on multiple prediction metrics. It also displays strong zero-shot generalization capabilities--effectively generalizing to other cities even when fine-tuned only on limited samples from a single city. Moreover, our method is general and can be readily extended to the next POI prediction task. For brevity, we refer to our model as Llama-Mob, and the corresponding results are included in this paper. Source codes are available at https://github.com/TANGHULU6/Llama3-8B-Mob.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。