用Transformer将轨迹数据编码为可理解的序列表示。
Encoding Agent Trajectories as Representations with Sequence Transformers
- 将轨迹视为离散位置序列，用Transformer建模
- 在多个真实与合成数据集上验证有效性
- 适用于轨迹分类、相似性判断等下游任务
时空数据面临与自然语言类似的挑战：位置序列的顺序性、长距离依赖关系以及位置的多重语义。本文提出一种新型模型，将高维时空轨迹表示为离散位置序列，并采用基于Transformer的神经网络架构进行编码。类似于语言模型，所提出的代理轨迹表示编码序列变换器（STARE）可通过监督任务（如分类）和自监督任务（如掩码建模）学习轨迹数据中的表示与结构。我们在多种合成及真实轨迹数据集上进行了实验，结果表明该模型能学习到对下游任务有用的有意义编码，包括区分标签和判断位置间的相似性。利用这些编码，我们还能够挖掘时空数据中代理与位置之间的关系。
原文摘要 · Abstract (English)
Spatiotemporal data faces many analogous challenges to natural language text including the ordering of locations (words) in a sequence, long range dependencies between locations, and locations having multiple meanings. In this work, we propose a novel model for representing high dimensional spatiotemporal trajectories as sequences of discrete locations and encoding them with a Transformer-based neural network architecture. Similar to language models, our Sequence Transformer for Agent Representation Encodings (STARE) model can learn representations and structure in trajectory data through both supervisory tasks (e.g., classification), and self-supervisory tasks (e.g., masked modelling). We present experimental results on various synthetic and real trajectory datasets and show that our proposed model can learn meaningful encodings that are useful for many downstream tasks including discriminating between labels and indicating similarity between locations. Using these encodings, we also learn relationships between agents and locations present in spatiotemporal data.
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。