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:2608. 03696v1 Announce Type: new Abstract: This work focuses on the problem of learning on temporal graphs, with particular emphasis on the task of clustering: obtaining coarse-grained representations by aggregating information from nodes, edges, and temporal dynamics - a task related to pooling in machine learning on graphs, or community detection in network science.
By Nelson Aloysio Reis de Almeida Passos, Emanuele Carlini, Salvatore Trani
arXiv:2606. 09100v1 Announce Type: cross Abstract: Community detection is a fundamental problem in the analysis of complex networks.
By Shahin Momenzadeh, Rojiar Pir Mohammadiani
ComNetX is a solver‑agnostic hierarchical adaptation framework that localizes dynamic community detection updates by expanding, closing, and contracting affected communities. It preserves the context needed by high‑quality solvers while restricting computation to the changed graph regions. Experiments on six real networks and synthetic streams show that ComNetX maintains modularity close to full recomputation while achieving up to a 41.9× speedup on large graphs.
By Aleksandr Konovalov, Anna Uporova, Alexander Drobyshev, Iaroslav Egorov, Grigoriy Bokov
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.
By William Cappelletti, \'Etienne Voutaz, Pascal Frossard
arXiv:2607. 17288v1 Announce Type: cross Abstract: High quality temporal graph benchmarks with rich semantics and ground-truth anomaly labels are essential for training graph neural networks, yet remain scarce due to privacy constraints and annotation costs.
By Jiacheng Ding, Xiaofei Zhang