Social network analysis using deep learning: applications and schemes
AM Abbas - Social Network Analysis and Mining, 2021 - Springer
Online social networks (OSNs) are part of daily life of human beings. Millions of users are
connected through online social networks. Due to very large number of users and huge …
connected through online social networks. Due to very large number of users and huge …
Topology identification method for residential areas in low-voltage distribution networks based on unsupervised learning and graph theory
H Li, W Liang, Y Liang, Z Li, G Wang - Electric Power Systems Research, 2023 - Elsevier
The information of a low-voltage (LV) distribution network is important for power supply
departments to monitor grid information, analyze faults and optimize grid operation status …
departments to monitor grid information, analyze faults and optimize grid operation status …
Compute optimization mechanism for deep neural networks
US12086705B2 - Compute optimization mechanism for deep neural networks - Google Patents
US12086705B2 - Compute optimization mechanism for deep neural networks - Google Patents …
US12086705B2 - Compute optimization mechanism for deep neural networks - Google Patents …
Network signatures from image representation of adjacency matrices: Deep/transfer learning for subgraph classification
K Hegde, M Magdon-Ismail, R Ramanathan… - arXiv preprint arXiv …, 2018 - arxiv.org
We propose a novel subgraph image representation for classification of network fragments
with the targets being their parent networks. The graph image representation is based on 2D …
with the targets being their parent networks. The graph image representation is based on 2D …
Gaussian Boson Sampling to Accelerate NP-Complete Vertex-Minor Graph Classification
M Sureka, S Guha - arXiv preprint arXiv:2402.03524, 2024 - arxiv.org
Gaussian Boson Sampling (GBS) generate random samples of photon-click patterns from a
class of probability distributions that are hard for a classical computer to sample from …
class of probability distributions that are hard for a classical computer to sample from …
Topology Identification Method for Low-Voltage Distribution Networks Based on Unsupervised Learning and Graph Theory
H Li, W Liang, Y Liang, Z Li, G Wang - Available at SSRN 4178876 - papers.ssrn.com
The information of a low-voltage (LV) distribution network is important for power supply
departments to monitor grid information, analyze faults and optimize grid operation status …
departments to monitor grid information, analyze faults and optimize grid operation status …
Network Lens: Node Classification in Topologically Heterogeneous Networks
K Hegde, M Magdon-Ismail - arXiv preprint arXiv:1901.09681, 2019 - arxiv.org
We study the problem of identifying different behaviors occurring in different parts of a large
heterogenous network. We zoom in to the network using lenses of different sizes to capture …
heterogenous network. We zoom in to the network using lenses of different sizes to capture …
The intrinsic scale of networks is small
M Magdon-Ismail, K Hegde - Proceedings of the 2019 IEEE/ACM …, 2019 - dl.acm.org
We define the intrinsic scale at which a network begins to reveal its identity as the scale at
which subgraphs in the network (created by a random walk) are distinguishable from similar …
which subgraphs in the network (created by a random walk) are distinguishable from similar …
Separating Terrorist-Like Topological Signatures Embedded in Benign Networks
K Hegde, M Magdon-Ismail - MILCOM 2018-2018 IEEE Military …, 2018 - ieeexplore.ieee.org
We study the problem of identifying topologically adversarial nodes in real networks using a
graph classification methodology. To test our approach, we implant nodes from a terrorist …
graph classification methodology. To test our approach, we implant nodes from a terrorist …
Использование матриц смежности для визуализации больших графов
ЗВ Апанович - Электронные библиотеки, 2019 - ellibs.elpub.ru
Аннотация Экспоненциальный рост размеров таких графов, как социальные сети,
интернет-графы и др., требует новых подходов к их визуализации. Наряду с …
интернет-графы и др., требует новых подходов к их визуализации. Наряду с …