LGAIJun 3

Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models

arXiv:2606.0467248.3
AI Analysis

For researchers working on dynamic graph representation learning, this work addresses the bottleneck of capturing long-range dependencies in continuous-time settings, offering a novel state-space modeling framework.

The paper tackles long-range spatio-temporal representation learning on continuous-time dynamic graphs. The proposed CTDG-SSM model achieves state-of-the-art performance on dynamic link prediction, node classification, and sequence classification, with significant gains on datasets requiring long-range temporal and spatial reasoning.

Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global structural patterns. To mitigate this, we derive a parameter-efficient state-space modeling framework for continuous-time dynamic graphs (CTDG-SSM) from first principles. We first introduce continuous-time Topology-Aware higher order polynomial projection operator (CTT-HiPPO), a novel memory-based reformulation of HiPPO to jointly encode temporal dynamics and graph structure. The solution from CTT-HiPPO is obtained by projecting the classical HiPPO solution through a polynomial of the Laplacian matrix, yielding topology-aware memory updates that admit an equivalent state-space formulation for CTDGs (CTDG-SSM). Then a computationally efficient discrete formulation is obtained using the zero-order hold approach for model implementation. Across benchmarks on dynamic link prediction, dynamic node classification, and sequence classification, CTDG-SSM achieves state-of-the-art performance. Notably, it achieves large performance gains on datasets that require long range temporal (LRT) and spatial reasoning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes