arXiv subjects

Nelson Aloysio Reis de Almeida Passos

Publications and source records attributed to Nelson Aloysio Reis de Almeida Passos.

3 recordsLinked to original sources

arXiv2026

Accelerating Dynamic Graph Clustering on GPU Architectures with cuGraph

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. Our multislice modularity backend achieves up to roughly three orders of magnitude speedup over the CPU reference under an equal-work budget, depending on graph density and snapshot count, while preserving compatibility with existing graph analytics pipelines. We demonstrate its applicability on real-world and synthetic datasets, facilitating exploratory analysis of structural network properties over time. Such capabilities are relevant across several application domains, such as epidemic spreading, financial systems, cybersecurity, and trajectory and mobility analysis. We release our implementation as free and open-source software, including Python bindings through the NetworkX-Temporal library for ease of use and zero-code acceleration with existing codebases.

cs.DC↗

arXiv2026

Learning and Clustering on Temporal Graphs: Principles, Primitives, and Pooling

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. Although graph neural networks reach state-of-the-art performance across many downstream graph tasks, their advantage over established descriptive and inferential clustering algorithms is far less settled, especially under demands of efficiency and recovery accuracy. We frame this tension through three linked perspectives: principles, connecting graph learning and community detection through shared spectral foundations and detectability thresholds in stochastic block model regimes; primitives, making spectral clustering and multislice modularity optimization tractable through GPU-accelerated temporal backends; and pooling, viewing principled community detection as a theory-grounded coarse-graining operator for temporal graphs. Our results indicate that algorithmic methods remain the appropriate tool where attributes are absent or weak - scalability rather than accuracy being the binding obstacle - while neural models are most compelling when structural, temporal, and attribute signals align. By making temporal clustering scalable, GPU-accelerated primitives suggest a route toward theory-grounded pooling, while raising a central question: when does community-based coarse-graining preserve the dynamics needed for downstream learning tasks?

cs.LG↗

arXiv2025

Time-varying ecological interactions characterise equilibrium and stability

Ecological communities are composed of species interactions that respond to environmental fluctuations. Despite increasing evidence of temporal variation in these interactions, most theoretical frameworks remain rooted in static assumptions. Here, we develop and apply a time-varying network model to five long-term ecological datasets spanning diverse taxa and environments. Using a generalized Lotka-Volterra framework with environmental covariates, we quantify temporal rewiring of interspecific interactions, asymmetry patterns, and structural stability. Our results reveal contrasting dynamics across ecosystems: in datasets with rich temporal resolution, interaction networks exhibit marked rewiring and shifts in cooperation-competition ratios that correlate with environmental stress, consistent, though not always linearly, with the stress-gradient hypothesis. Conversely, in datasets with coarser temporal sampling, networks retain constant interaction sign structure and remain in cooperation-dominated regimes. These findings highlight the importance of temporal resolution and environmental context in shaping ecological coexistence.

q-bio.PE↗