Network Analysis Resources & Updates
3.09K subscribers
848 photos
163 files
1.15K links
Are you seeking assistance or eager to collaborate?
Don't hesitate to dispatch your insights, inquiries, proposals, promotions, bulletins, announcements, and more to our channel overseer. We're all ears!

Contact: @Questioner2
Download Telegram
🎞 Machine Learning with Graphs: Deep Generative Models for Graphs, Graph RNN: Generating Realistic Graphs, Scaling Up & Evaluating Graph Gen, Applications of Deep Graph Generation.


πŸ’₯Free recorded course by Jure Leskovec, Computer Science, PhD

πŸ’₯this lecture, focus on deep generative models for graphs. We outline 2 types of tasks within the problem of graph generation: (1) realistic graph generation, where the goal is to generate graphs that are similar to a given set of graphs; (2) goal-directed graph generation, where we want to generate graphs that optimize given objectives/constraints. First, we recap the basics for generative models and deep generative models; then, in next parts introduce and focus on GraphRNN, one of the first deep generative models for graph; and finally, discuss GCPN, a deep graph generative model designed specifically for application to molecule generation.

πŸ“½ Watch: part1 part2 part3 part4

πŸ“²Channel: @ComplexNetworkAnalysis

#video #course #Graph #Machine_Learning #GCPN #GraphRNN #DGNN #GNN
πŸ‘3πŸŽ‰1
2018-Structure-oriented prediction in complex networks.pdf
2.9 MB
πŸ“„Structure-oriented prediction in complex networks

πŸ“˜ Journal: Physics Reports (IF=25.6)
πŸ—“Publish year: 2018

πŸ“ŽStudy paper

πŸ“²Channel: @ComplexNetworkAnalysis
#paper #prediction
πŸ‘4
πŸ“„Do we need deep graph neural networks?

πŸ’₯Technical paper

πŸ’₯ One of the hallmarks of deep learning was the use of neural networks with tens or even hundreds of layers. In stark contrast, most of the architectures used in graph deep learning are shallow with just a handful of layers. In this post, I raise a heretical question: does depth in graph neural network architectures bring any advantage?

🌐 Study

πŸ“²Channel: @ComplexNetworkAnalysis

#paper #Graph #DGNN
πŸ‘5
πŸ“„GCN-tutorial

πŸ’₯Technical paper

πŸ’₯ Graph Convolutional Network. Perform convolution operations on a graph using the information embedded into each node. The main idea is to "look" at neighboor nodes and update the currently embedded information into a higher or lower dimensional space by performing a ReLU or softmax operation.

🌐 Study

πŸ“²Channel: @ComplexNetworkAnalysis

#paper #Graph #code #python #GCN #Coda
πŸ‘3
πŸ“„A Review on Graph Neural Network Methods in Financial Applications

πŸ—“Publish year: 2022

πŸ“ŽStudy paper

πŸ“±Channel: @ComplexNetworkAnalysis
#paper #GNN #Financial #Applications #review
πŸ“„Applications of social network analysis in promoting circular economy: a literature review

πŸ“˜ Published by Vilnius Gediminas Technical University.
πŸ—“Publish year: 2023

πŸ“ŽStudy paper

πŸ“²Channel: @ComplexNetworkAnalysis
#paper #social_network #review #economy
πŸ‘3
πŸŽ“Towards a deeper understanding of the Visibility Graph algorithm

πŸ“˜Master’s Thesis, in the Delft University of Technolog, T.J. Alers

πŸ—“Publish year: 2023

πŸ“ŽStudy Thesis

πŸ“²Channel: @ComplexNetworkAnalysis

#Thesis #Visibility_Graph
πŸ‘3πŸ‘2
2023_A_survey_of_graph_neural_network_based_recommendation_in_social.pdf
1.6 MB
πŸ“„A survey of graph neural network based recommendation in social networks

πŸ“˜ Journal: Neurocomputing (IF=6)
πŸ—“Publish year: 2023

πŸ“ŽStudy paper

πŸ“±Channel: @ComplexNetworkAnalysis
#paper #GNN #Recommendation #survey
πŸ‘3πŸ‘2
πŸ“„A Survey of Recommendation Systems: Recommendation Models, Techniques, and Application Fields

πŸ“˜ Journal: Electronics (IF=2.9)
πŸ—“Publish year: 2022

πŸ“ŽStudy paper

πŸ“±Channel: @ComplexNetworkAnalysis
#paper #Recommendation_Systems #Techniques #Application #survey
πŸ‘4
πŸ“„A Review on Graph Neural Network Methods in Financial Applications

πŸ“˜ Journal: Mental Health and Social Inclusion (IF=1.2)
πŸ—“Publish year: 2023

πŸ“ŽStudy paper

πŸ“±Channel: @ComplexNetworkAnalysis
#paper #GNN #Financial #Application #review
πŸ‘1
πŸ“„The Four Dimensions of Social Network Analysis: An Overview of Research Methods, Applications, and Software Tools

πŸ—“Publish year: 2020

πŸ“ŽStudy paper

πŸ“±Channel: @ComplexNetworkAnalysis
#paper #Dimensions #Methods #Application #Software #Tools #Overview
❀2
πŸ“•Graph Representation Learning

πŸ’₯Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial if we want systems that can learn, reason, and generalize from this kind of data. Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of convolutional neural networks to graph-structured data, and neural message-passing approaches inspired by belief propagation. These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D-vision, recommender systems, question answering, and social network analysis.

🌐 Read online

πŸ“²Channel: @ComplexNetworkAnalysis

#book #GRL #GNN
πŸ‘3❀1
πŸ“„A Review of Link Prediction Applications in Network Biology

πŸ—“Publish year: 2023

πŸ“ŽStudy paper

πŸ“±Channel: @ComplexNetworkAnalysis
#paper #Link_Prediction #Application #Biology #review
πŸ‘4
πŸŽ“A study of visibility graphs for time series representations

πŸ“˜Bachelor’s Thesis, in the University Polytechnica de catalunya barcelonatech, Bergillos Varela, Carlos
πŸ—“Publish year: 2020

πŸ“ŽStudy Thesis

πŸ“²Channel: @ComplexNetworkAnalysis

#Thesis #Visibility_Graph
πŸ‘4
🎞 Promise and perils of population-scale social network analysis

πŸ’₯Free recorded presentation by Frank Takes.

πŸ’₯A relatively recently emerging line of research is devoted to the use of large-scale population register data to answer enduring questions in the realm of social science. In this presentation, it specifically delves into the network dimension of such data, focusing on information from the POPNET project, which covers more than 17 million people (i.e., the entire population of the Netherlands) and approximately 800 million family, household, school, work, and neighbor-to-neighbor connections. The presentation highlights the potential inherent in this comprehensive and curated social network data through illustrative examples of results related to issues such as social capital, segregation, and migration. Additionally, it will examine several methodological considerations and challenges related to under- and over-sampling of individual connections within opportunity structures, including findings on the validity of real-world skewed degree distributions.

πŸ“½ Watch

πŸ“±Channel: @ComplexNetworkAnalysis

#video #Promise #perils #population_scale