2021-Graphnet Graph Clustering with Deep Neural Networks.pdf
2.3 MB
πGraphnet: Graph Clustering with Deep Neural Networks
π Conference: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
πPublish year: 2021
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #Graphnet #Deep_Neural_Networks #Clustering
π Conference: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
πPublish year: 2021
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #Graphnet #Deep_Neural_Networks #Clustering
π2β€1
π Anomaly Detection: Algorithms, Explanations, Applications
π₯Free recorded tutorial by Dr. Dietterichβs.He is part of the leadership team for OSUβs Ecosystem Informatics programs including the NSF Summer Institute in Ecoinformatics
π₯Anomaly detection is important for data cleaning, cybersecurity, and robust AI systems. This talk will review recent work in our group on (a) benchmarking existing algorithms, (b) developing a theoretical understanding of their behavior, (c) explaining anomaly βalarmsβ to a data analyst, and (d) interactively re-ranking candidate anomalies in response to analyst feedback. Then the talk will describe two applications: (a) detecting and diagnosing sensor failures in weather networks and (b) open category detection in supervised learning.
π½ Watch
π±Channel: @ComplexNetworkAnalysis
#video #Anomaly_Detection #Algorithms #Explanations #Applications
π₯Free recorded tutorial by Dr. Dietterichβs.He is part of the leadership team for OSUβs Ecosystem Informatics programs including the NSF Summer Institute in Ecoinformatics
π₯Anomaly detection is important for data cleaning, cybersecurity, and robust AI systems. This talk will review recent work in our group on (a) benchmarking existing algorithms, (b) developing a theoretical understanding of their behavior, (c) explaining anomaly βalarmsβ to a data analyst, and (d) interactively re-ranking candidate anomalies in response to analyst feedback. Then the talk will describe two applications: (a) detecting and diagnosing sensor failures in weather networks and (b) open category detection in supervised learning.
π½ Watch
π±Channel: @ComplexNetworkAnalysis
#video #Anomaly_Detection #Algorithms #Explanations #Applications
YouTube
Anomaly Detection: Algorithms, Explanations, Applications
Anomaly detection is important for data cleaning, cybersecurity, and robust AI systems. This talk will review recent work in our group on (a) benchmarking existing algorithms, (b) developing a theoretical understanding of their behavior, (c) explaining anomalyβ¦
π2
πCurrent and future directions in network biology
πPublish year: 2023
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #graph #biology
πPublish year: 2023
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #graph #biology
β€2
π Network data visualization in Gephi
π₯Dr. Daria Maltseva, PhD, Head, International Laboratory for Applied Network Research, HSE.
π₯14th Summer School 'Methods and Tools for Social Network Analysis'.
π½ Watch
π±Channel: @ComplexNetworkAnalysis
#video #Network #data #visualization #Gephi
π₯Dr. Daria Maltseva, PhD, Head, International Laboratory for Applied Network Research, HSE.
π₯14th Summer School 'Methods and Tools for Social Network Analysis'.
π½ Watch
π±Channel: @ComplexNetworkAnalysis
#video #Network #data #visualization #Gephi
YouTube
14th SS 2023. Day 2. Network data visualization in Gephi
Tamara Shcheglova, Doctoral student, Junior Research Fellow, Visiting Lecturer, International laboratory for Applied Network Research, HSE
π1π1
πGraph Neural Networks in IoT: A Survey
πPublish year: 2022
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #GNN #IOT #survey
πPublish year: 2022
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #GNN #IOT #survey
π2
πStatistical Network Analysis: Past, Present, and Future
πPublish year: 2023
πStudy paper
π±Channel: @ComplexNetworkAnalysis
#paper #Statistical_Network #Past #Present #Future
πPublish year: 2023
πStudy paper
π±Channel: @ComplexNetworkAnalysis
#paper #Statistical_Network #Past #Present #Future
β€1π1
π Social Network Analysis | Chapter 4 | Link Analysis | Part 2
π₯This is supplementary material for the book Social Network Analysis by Dr. Tanmoy Chakraborty.
π½ Watch
π±Channel: @ComplexNetworkAnalysis
#video #Link_Analysis
π₯This is supplementary material for the book Social Network Analysis by Dr. Tanmoy Chakraborty.
π½ Watch
π±Channel: @ComplexNetworkAnalysis
#video #Link_Analysis
YouTube
Social Network Analysis | Chapter 4 | Link Analysis | Part 2
This is supplementary material for the book Social Network Analysis by Dr. Tanmoy Chakraborty.
Book Website: https://social-network-analysis.in/
Available for purchase at: https://www.amazon.in/Social-Network-Analysis-Tanmoy-Chakraborty/dp/9354247830
Book Website: https://social-network-analysis.in/
Available for purchase at: https://www.amazon.in/Social-Network-Analysis-Tanmoy-Chakraborty/dp/9354247830
β€1
πA Gentle Introduction to Graph Neural Networks
π₯Technical online article
π Study
π²Channel: @ComplexNetworkAnalysis
#online_book #Graph #GNN
π₯Technical online article
π Study
π²Channel: @ComplexNetworkAnalysis
#online_book #Graph #GNN
Distill
A Gentle Introduction to Graph Neural Networks
What components are needed for building learning algorithms that leverage the structure and properties of graphs?
π5
π Machine Learning with Graphs: Generative Models for Graphs, Erdos Renyi Random Graphs, The Small World Model, Kronecker Graph Model
π₯Free recorded course by Jure Leskovec, Computer Science, PhD
π₯This lecture, will cover generative models for graphs. The goal of generative models for graphs is to generate synthetic graphs which are similar to given example graphs. The simplest model for graph generation, ErdΓΆs-Renyi graph (E-R graphs, Gnp graphs). The small-world graphs (WattsβStrogatz graphs, W-S graphs). Even though the E-R graphs can fit the average path length of real-world graphs, its clustering coefficient is much smaller than real-world graphs. The small-world model is proposed to generative realistic graphs with both low diameter and high clustering coefficient. Specifically, W-S graphs are generative by randomly rewring edges from regular lattic graphs. The Kronecker Graph model, where graphs are generated in a recursive manner. The key motivation is that real-world graphs often exhibit self-similarity, where the whole structure of the graph has the same shape as its parts. Kronecker graphs are generated by recursively doing Kronecker product over the initiator matrix, which is trained to fit the statistics of the input dataset. We further discuss fast Kronecker generator algorithms. Finally, we show that Kronecker graphs and real graphs are very close in many important graph statistics.
π½ Watch: part1 part2 part3 part4
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #Erdos_Renyi #Small_World #Kronecker_Graph
π₯Free recorded course by Jure Leskovec, Computer Science, PhD
π₯This lecture, will cover generative models for graphs. The goal of generative models for graphs is to generate synthetic graphs which are similar to given example graphs. The simplest model for graph generation, ErdΓΆs-Renyi graph (E-R graphs, Gnp graphs). The small-world graphs (WattsβStrogatz graphs, W-S graphs). Even though the E-R graphs can fit the average path length of real-world graphs, its clustering coefficient is much smaller than real-world graphs. The small-world model is proposed to generative realistic graphs with both low diameter and high clustering coefficient. Specifically, W-S graphs are generative by randomly rewring edges from regular lattic graphs. The Kronecker Graph model, where graphs are generated in a recursive manner. The key motivation is that real-world graphs often exhibit self-similarity, where the whole structure of the graph has the same shape as its parts. Kronecker graphs are generated by recursively doing Kronecker product over the initiator matrix, which is trained to fit the statistics of the input dataset. We further discuss fast Kronecker generator algorithms. Finally, we show that Kronecker graphs and real graphs are very close in many important graph statistics.
π½ Watch: part1 part2 part3 part4
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #Erdos_Renyi #Small_World #Kronecker_Graph
YouTube
Stanford CS224W: Machine Learning with Graphs | 2021 | Lecture 14.1 - Generative Models for Graphs
For more information about Stanfordβs Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3jO8OsE
Jure Leskovec
Computer Science, PhD
In this lecture, we will cover generative models for graphs. The goal of generativeβ¦
Jure Leskovec
Computer Science, PhD
In this lecture, we will cover generative models for graphs. The goal of generativeβ¦
π5
2022_A_review_of_challenges_and_solutions_in_the_design_and_implementation.pdf
2 MB
πA review of challenges and solutions in the design and implementation of deep graph neural networks
π journal: Artificial Intelligence Review (I.F=0.381)
πPublish year: 2022
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #review #GNN #implementation
π journal: Artificial Intelligence Review (I.F=0.381)
πPublish year: 2022
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #review #GNN #implementation
π2π2
πEverything is connected: Graph neural networks
π journal: Current Opinion in Structural Biology (I.F=6.8)
πPublish year: 2022
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #GNN
π journal: Current Opinion in Structural Biology (I.F=6.8)
πPublish year: 2022
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #GNN
π3π1
πGraph Representation Learning
π Journal: European Symposium on Artificial Neural Networks
πPublish year: 2023
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #representation
π Journal: European Symposium on Artificial Neural Networks
πPublish year: 2023
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #representation
π2
πDeep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence
π Journal: International journal of intelligent systems (IF=7)
πPublish year: 2023
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #GCN #overview
π Journal: International journal of intelligent systems (IF=7)
πPublish year: 2023
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #GCN #overview
π3β€1
π Machine Learning with Graphs: Deep Generative Models for Graphs, Graph RNN: Generating Realistic Graphs, Scaling Up & Evaluating Graph Gen, Applications of Deep Graph Generation.
π₯Free recorded course by Jure Leskovec, Computer Science, PhD
π₯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.
π½ Watch: part1 part2 part3 part4
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #GCPN #GraphRNN #DGNN #GNN
π₯Free recorded course by Jure Leskovec, Computer Science, PhD
π₯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.
π½ Watch: part1 part2 part3 part4
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #GCPN #GraphRNN #DGNN #GNN
YouTube
Stanford CS224W: ML with Graphs | 2021 | Lecture 15.1 - Deep Generative Models for Graphs
For more information about Stanfordβs Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3Ex8TsH
Jure Leskovec
Computer Science, PhD
In this lecture, we focus on deep generative models for graphs. We outline 2 types ofβ¦
Jure Leskovec
Computer Science, PhD
In this lecture, we focus on deep generative models for graphs. We outline 2 types ofβ¦
π3π1
2018-Structure-oriented prediction in complex networks.pdf
2.9 MB
πStructure-oriented prediction in complex networks
π Journal: Physics Reports (IF=25.6)
πPublish year: 2018
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #prediction
π Journal: Physics Reports (IF=25.6)
πPublish year: 2018
πStudy paper
π²Channel: @ComplexNetworkAnalysis
#paper #prediction
π4
π application of machine learning in traffic optimization
π₯Free recorded course by Powel gora
π½ Watch
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning
π₯Free recorded course by Powel gora
π½ Watch
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning
YouTube
PaweΕ Gora: Applications of machine learning in traffic optimization
I will be talking about possible applications of machine learning in traffic optimization (and in optimizing some other complex processes). I will describe the process of building traffic metamodels by approximating outcomes of traffic simulations using machineβ¦
π4
πDo we need deep graph neural networks?
π₯Technical paper
π₯ 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?
π Study
π²Channel: @ComplexNetworkAnalysis
#paper #Graph #DGNN
π₯Technical paper
π₯ 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?
π Study
π²Channel: @ComplexNetworkAnalysis
#paper #Graph #DGNN
Medium
Do we need deep graph neural networks?
Is βgraph deep learningβ a misnomer and is depth useful for graph neural networks?
π5
πGCN-tutorial
π₯Technical paper
π₯ 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.
π Study
π²Channel: @ComplexNetworkAnalysis
#paper #Graph #code #python #GCN #Coda
π₯Technical paper
π₯ 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.
π Study
π²Channel: @ComplexNetworkAnalysis
#paper #Graph #code #python #GCN #Coda
π3
π pytorch geometric tutorial: graph attention networks implementation
π₯Free recorded course
π½ Watch
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #GAT #code #python
π₯Free recorded course
π½ Watch
π²Channel: @ComplexNetworkAnalysis
#video #course #Graph #GAT #code #python
YouTube
Pytorch Geometric tutorial: Graph attention networks (GAT) implementation
In this video we will see the math behind GAT and a simple implementation in Pytorch geometric.
Outcome:
- Recap
- Introduction
- GAT
- Message Passing pytroch layer
- Simple GCNlayer implementation
- GAT implementation
- GAT Usage
Download the materialβ¦
Outcome:
- Recap
- Introduction
- GAT
- Message Passing pytroch layer
- Simple GCNlayer implementation
- GAT implementation
- GAT Usage
Download the materialβ¦
π2