arXiv:2606. 07151v1 Announce Type: new Abstract: Traditional change point detection in dynamic networks assumes abrupt transitions between stationary states, overlooking scenarios of continuous evolution which arise in most real-world applications, such as social networks or physical systems.
arXiv:2605. 21514v2 Announce Type: replace-cross Abstract: Diffusion-based information-theoretic approaches provide new theoretical and practical tools to study complex networks.
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. 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:2608. 03695v1 Announce Type: cross Abstract: This work addresses community detection in temporal networks through GPU-accelerated extensions of spectral clustering and modularity-based algorithms originally designed for static graphs.
This work addresses community detection in temporal networks through GPU-accelerated extensions of spectral clustering and modularity-based algorithms originally designed for static graphs. Built on the NVIDIA RAPIDS ecosystem, the framework enables the characterization and tracking of communities in snapshot-based dynamic graphs, either by Leiden greedy optimization with multi-GPU support via Dask-based workload distribution, or eigendecomposition of a symmetric Bethe-Hessian operator.
arXiv:2405. 19062v2 Announce Type: replace-cross Abstract: Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems.
arXiv:2606. 00304v1 Announce Type: new Abstract: Graph anomaly detection methods aim to distinguish anomalous nodes.
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.
The paper investigates root cause analysis for anomalies in linear time-series data by using difference graph discovery. It focuses on effect-defying root causes—variables whose causal coefficients differ between normal and anomalous regimes—within linear discrete-time dynamic structural causal models. The authors adapt existing difference graph methods to the time-series context, evaluate them on simulated data, and apply them to real-world IT and intensive care monitoring datasets to localize causal mechanisms behind anomalous behavior.
The paper explores how information propagates in Deep Graph Networks (DGNs) for both static and dynamic graphs, treating DGNs as dynamical systems. It presents new architectures that better preserve long‑term node dependencies and learn complex spatio‑temporal patterns from irregular, sparsely sampled dynamic graphs. The work combines theoretical analysis with empirical results to demonstrate the effectiveness of these designs.
Diffusion models represent a leading paradigm for graph generation, with notable impact in domains such as molecular design. Yet, scaling these models to large graphs remains an open problem.
arXiv:2606. 05636v1 Announce Type: new Abstract: Root-Cause Analysis (RCA) seeks to identify the variables responsible for abnormal system behavior in complex domains such as manufacturing, cloud computing, and healthcare.