AI 中文总结
针对多变量时空数据应用中现有深度子空间聚类方法的局限，提出CASC框架，集成特定架构保留时空结构，引入自表达网络建模多种关系，还提出两个新学习目标，将其转变为因果-时间状态发现框架。
AI 中文摘要
深度子空间聚类在海冰监测、疾病传播分析和神经退化跟踪等多变量时空数据应用中起着关键作用。现有方法主要依赖几何自表达性，假设静态子空间结构，常无法捕捉复杂时空系统中的因果依赖、局部空间相互作用和长期时间动态。为解决这些局限，我们提出了一种新颖的因果对抗子空间聚类（CASC）框架，用于在高维时空数据中发现不断演变的潜在状态。CASC集成了受U-Net启发的深度对抗聚类架构与堆叠的FAConvLSTM层，以在学习鲁棒潜在表示时保留空间和时间结构。引入了基于图注意力变换器的自表达网络来联合建模局部空间关系、全局依赖和长期时间相互作用。此外，我们提出了两个新的学习目标：因果子空间保留损失和动态时间子空间演化损失。这些组件共同将深度子空间聚类从相关驱动范式转变为因果-时间状态发现框架。
英文摘要
Deep subspace clustering plays a critical role in applications involving multivariate spatiotemporal data, such as sea ice monitoring, disease spread analysis, and tracking neuro-degeneration over time. Despite recent advances, existing methods primarily rely on geometric self-expressiveness, assume static subspace structures, and often fail to capture causal dependencies, local spatial interactions, and long-range temporal dynamics inherent in complex spatiotemporal systems. To address these limitations, we propose a novel Causal Adversarial Subspace Clustering (CASC) framework for discovering evolving latent regimes in high-dimensional spatiotemporal data. CASC integrates a U-Net-inspired deep adversarial clustering architecture with stacked FAConvLSTM layers to preserve spatial and temporal structure while learning robust latent representations. A graph attention transformer-based self-expressive network is introduced to jointly model local spatial relationships, global dependencies, and long-range temporal interactions. Furthermore, we propose two new learning objectives: (1) a Causal Subspace Preservation Loss that aligns self-expression coefficients with latent causal relationships, encouraging clusters to reflect underlying causal processes rather than simple feature similarity, and (2) a Dynamic Temporal Subspace Evolution Loss that captures evolving subspace structures and temporal regime transitions in nonstationary environments. Together, these components transform deep subspace clustering from a correlation-driven paradigm into a causal-temporal regime discovery framework.
Comments10 pages
Journal refIEEE International Conference on Data Mining (ICDM 2026)
