NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imaging

no code implementations • 23 Sep 2023 • Nirhoshan Sivaroopan, Dumindu Bandara, Chamara Madarasingha, Guilluame Jourjon, Anura Jayasumana, Kanchana Thilakarathna

Network data analytics are now at the core of almost every networking solution.

Anomaly Detection Time Series +1

A Pre-training Oracle for Predicting Distances in Social Networks

no code implementations • 6 Jun 2021 • Gunjan Mahindre, Randy Paffenroth, Anura Jayasumana, Rasika Karkare

OSP can be easily extended to other domains such as random networks by choosing an appropriate model to generate synthetic training data, and therefore promises to impact many different network learning problems.

Low-Rank Matrix Completion

Adversarial Data Generation of Multi-category Marked Temporal Point Processes with Sparse, Incomplete, and Small Training Samples

no code implementations • 1 Jan 2021 • Shashika Ranga Muramudalige, Anura Jayasumana, Haonan Wang

The transformation of training data to the distribution facilitates the accurate capture of underlying process characteristics despite the sparseness and incompleteness of data.

Point Processes