CTDG-SSM introduces CTT-HiPPO, a Laplacian-polynomial projection of HiPPO, to create a parameter-efficient state-space formulation for continuous-time dynamic graphs that captures long-range spatio-temporal patterns.
Representation Learning over Dynamic Graphs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embeddings drive the dynamics of two key processes namely, communication and association between nodes in dynamic graphs. These processes exhibit complex nonlinear dynamics that evolve at different time scales and subsequently contribute to the update of node embeddings. We employ a time-scale dependent multivariate point process model to capture these dynamics. We devise an efficient unsupervised learning procedure and demonstrate that our approach significantly outperforms representative baselines on two real-world datasets for the problem of dynamic link prediction and event time prediction.
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A 13-coordinate leakage-safe motif feature map derived from three empirical axes of temporal motif activity improves TGNN performance on link prediction and edge classification across multiple real and synthetic datasets.
citing papers explorer
-
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
CTDG-SSM introduces CTT-HiPPO, a Laplacian-polynomial projection of HiPPO, to create a parameter-efficient state-space formulation for continuous-time dynamic graphs that captures long-range spatio-temporal patterns.
-
Temporal Motif Signatures for Temporal Graph Neural Networks
A 13-coordinate leakage-safe motif feature map derived from three empirical axes of temporal motif activity improves TGNN performance on link prediction and edge classification across multiple real and synthetic datasets.