MambaTG is a new framework for future link prediction on temporal graphs that addresses both repeated and unseen edge prediction. It leverages two complementary signals: the historical-sequence evolution of a node’s interactions and the compatibility between a candidate edge and the node’s evolving history. By using a candidate-aware Mamba architecture, the model captures ordered interaction dynamics and adapts state transitions to different candidates, achieving strong performance across 13 datasets while remaining computationally efficient.
Future link prediction on temporal graphs involves both repeated interactions between previously connected node pairs and first-time interactions between pairs with no prior interaction. While repeate...
arXiv:2610.19364v1 Announce Type: new Abstract: Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do...
The paper investigates whether temporal link predictors can forgo learned node representations in favor of simple statistical counts of interaction patterns. It introduces a predictor that aggregates transition and co‑occurrence counts, smooths them with destination frequencies or Kneser‑Ney continuation counts, and combines these with popularity, source history, and recency via a shared log‑linear rule. With only 9–13 learned parameters, the model achieves the best mean reciprocal rank on 7 of 16 datasets and outperforms several baselines across all evaluated datasets, demonstrating that a lightweight, count‑based approach can rival more complex neural methods.
arXiv:2607. 07716v1 Announce Type: cross Abstract: Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy.
arXiv:2610.27558v1 Announce Type: cross Abstract: Memory-based temporal graph neural networks (TGN) rely on recurrent node memories to capture evolving interaction histories. However, temporal mini-b...
arXiv:2602. 14239v3 Announce Type: replace-cross Abstract: Predicting links in sparse, continuously evolving networks is a central challenge in network science.
AtlasULP introduces a relation atlas that captures both global and local structural associations between node pairs, providing a comprehensive representation for link prediction across diverse graph domains. The framework employs a domain-guided prompting model that generates domain-aware prompt tokens from contextual structures, enabling adaptive in-context prediction. Experiments show that AtlasULP consistently outperforms state‑of‑the‑art methods on a variety of graph domains.
The paper introduces the Graph Dynamics Model (GDM), a world model that learns stochastic latent dynamics over evolving graph topologies. GDM employs a sparse recurrent adjacency matrix for topology updates and a recurrent state‑space architecture for stochastic transitions, enabling it to handle partially observable, stochastic environments. The authors also propose the Graph Distribution Distance (GDD) metric, using maximum mean discrepancy with a graph kernel, to compare predicted and true joint graph state distributions, and demonstrate GDM’s superior performance and zero‑shot generalisation on large graphs.
arXiv:2607.23556v3 Announce Type: replace-cross Abstract: Temporal graphs are increasingly used to model dynamic systems across diverse domains, including social, financial, and traffic networks. Pre...
arXiv:2510. 09416v4 Announce Type: replace Abstract: Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models.
arXiv:2607. 23556v1 Announce Type: cross Abstract: Temporal graphs are increasingly used to model dynamic systems in diverse domains such as social networks, financial networks, and traffic networks.
arXiv:2606. 04672v1 Announce Type: cross Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data.