Dynamical behaviors of complex interacting systems, including brain activities, financial price movements, and physical collective phenomena, are associated with underlying interactions between the system's components. The issue of uncovering interaction relations in such systems using observable dynamics is called relational inference. In this study, we propose a Diffusion model for Relational Inference (DiffRI), inspired by a self-supervised method for probabilistic time series imputation. DiffRI learns to infer the probability of the presence of connections between components through conditional diffusion modeling. Experiments on both simulated and quasi-real datasets show that DiffRI is highly competent compared with other state-of-the-art models in discovering ground truth interactions in an unsupervised manner. Our code will be made public soon.

翻译：复杂相互作用系统的动力学行为，包括大脑活动、金融价格波动以及物理集体现象，均与系统组件之间的潜在相互作用相关联。利用可观测动力学揭示此类系统中的相互作用关系，这一研究问题被称为关系推理。本研究提出了一种用于关系推理的扩散模型（DiffRI），其灵感来源于一种基于自监督方法的概率时间序列插值技术。DiffRI通过条件扩散建模，学习推断组件之间连接存在的概率。在模拟数据集和准真实数据集上的实验表明，相较于其他最先进模型，DiffRI在无监督方式下发现真实交互关系方面具有显著优势。我们的代码将很快公开。