๐ Machine Learning with Graphs: Generative Models for Graphs, Erdos Renyi Random Graphs, The Small World Model, Kronecker Graph Model
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฅThis 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, Erdรถs-Renyi graph (E-R graphs, Gnp graphs). The small-world graphs (WattsโStrogatz 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.
๐ฝ Watch: part1 part2 part3 part4
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #Erdos_Renyi #Small_World #Kronecker_Graph
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฅThis 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, Erdรถs-Renyi graph (E-R graphs, Gnp graphs). The small-world graphs (WattsโStrogatz 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.
๐ฝ Watch: part1 part2 part3 part4
๐ฒChannel: @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 Stanfordโs 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 generativeโฆ
Jure Leskovec
Computer Science, PhD
In this lecture, we will cover generative models for graphs. The goal of generativeโฆ
๐5
๐ Machine Learning with Graphs: Deep Generative Models for Graphs, Graph RNN: Generating Realistic Graphs, Scaling Up & Evaluating Graph Gen, Applications of Deep Graph Generation.
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฅthis 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.
๐ฝ Watch: part1 part2 part3 part4
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #GCPN #GraphRNN #DGNN #GNN
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฅthis 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.
๐ฝ Watch: part1 part2 part3 part4
๐ฒChannel: @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 Stanfordโs 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 ofโฆ
Jure Leskovec
Computer Science, PhD
In this lecture, we focus on deep generative models for graphs. We outline 2 types ofโฆ
๐3๐1
๐ application of machine learning in traffic optimization
๐ฅFree recorded course by Powel gora
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning
๐ฅFree recorded course by Powel gora
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning
YouTube
Paweล 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 machineโฆ
๐4
๐ Machine Learning with Graphs: Applications of Deep Graph Generation.
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #DGNN #GNN
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #DGNN #GNN
YouTube
Stanford CS224W: ML with Graphs | 2021 | Lecture 15.4 - Applications of Deep Graph Generation
For more information about Stanfordโs Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3EwmakW
Lecture 15.4: Application of Deep Graph Generative Models to Molecule Generation
Jure Leskovec
Computer Science, PhD
Finallyโฆ
Lecture 15.4: Application of Deep Graph Generative Models to Molecule Generation
Jure Leskovec
Computer Science, PhD
Finallyโฆ
๐5โค1
๐Graph Attention Networks
๐ฅTechnical paper
๐ Study
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Graph #GAT #Machine_Learning #Attention #Neural_Network
๐ฅTechnical paper
๐ Study
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Graph #GAT #Machine_Learning #Attention #Neural_Network
Baeldung on Computer Science
Graph Attention Networks | Baeldung on Computer Science
Explore graph neural networks that use attention.
๐4
๐ Machine Learning with Graphs: Generative Models for Graphs
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฅIn this lecture, we 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. Graph generation is important as it can offer insight on the formulation process of graphs, which is crucial for predictions, simulations and anomaly detections on graphs. In the first part, we will introduce the properties of real-world graphs, where a successful graph generative model should fit these properties. These graph statistics include degree distribution, clustering coefficient, connected components and path length.
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #Generative_Models
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฅIn this lecture, we 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. Graph generation is important as it can offer insight on the formulation process of graphs, which is crucial for predictions, simulations and anomaly detections on graphs. In the first part, we will introduce the properties of real-world graphs, where a successful graph generative model should fit these properties. These graph statistics include degree distribution, clustering coefficient, connected components and path length.
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #Generative_Models
YouTube
Stanford CS224W: Machine Learning with Graphs | 2021 | Lecture 14.1 - Generative Models for Graphs
For more information about Stanfordโs 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 generativeโฆ
Jure Leskovec
Computer Science, PhD
In this lecture, we will cover generative models for graphs. The goal of generativeโฆ
๐6
๐ Graph Analytics and Graph-based Machine Learning
๐ฅFree recorded course by Clair Sullivan(Neo4j)
๐ฅMachine learning has traditionally revolved around creating models around data that is characterized by embeddings attributed to individual observations. However, this ignores a signal that could potentially be very strong: the relationships between data points. Network graphs provide great opportunities for identifying relationships that we may not even realize exist within our data. Further, a variety of methods exist to create embeddings of graphs that can enrich models and provide new insights.
In this talk we will look at some examples of common ML problems and demonstrate how they can take advantage of graph analytics and graph-based machine learning. We will also demonstrate how graph embeddings can be used to enhance existing ML pipelines.
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning
๐ฅFree recorded course by Clair Sullivan(Neo4j)
๐ฅMachine learning has traditionally revolved around creating models around data that is characterized by embeddings attributed to individual observations. However, this ignores a signal that could potentially be very strong: the relationships between data points. Network graphs provide great opportunities for identifying relationships that we may not even realize exist within our data. Further, a variety of methods exist to create embeddings of graphs that can enrich models and provide new insights.
In this talk we will look at some examples of common ML problems and demonstrate how they can take advantage of graph analytics and graph-based machine learning. We will also demonstrate how graph embeddings can be used to enhance existing ML pipelines.
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning
YouTube
Graph Analytics and Graph-based Machine Learning
Machine learning has traditionally revolved around creating models around data that is characterized by embeddings attributed to individual observations. However, this ignores a signal that could potentially be very strong: the relationships between dataโฆ
๐4๐1
๐Machine Learning for Refining Knowledge Graphs: A Survey
๐ Journal: acm digital library (I.F=14.324)
๐Publish year: 2020
๐Study paper
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Machine_Learning #Knowledge_Graphs #Survey
๐ Journal: acm digital library (I.F=14.324)
๐Publish year: 2020
๐Study paper
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Machine_Learning #Knowledge_Graphs #Survey
๐ฅ4๐2๐1
๐น Graph Embedding For Machine Learning in Python
๐ฅIn this video, you will learn how to embed graphs into n-dimensional space to use them for machine learning.
๐ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #Graph_Embedding #Machine_Learning
๐ฅIn this video, you will learn how to embed graphs into n-dimensional space to use them for machine learning.
๐ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #Graph_Embedding #Machine_Learning
YouTube
Graph Embedding For Machine Learning in Python
In this video, we learn how to embed graphs into n-dimensional space to use them for machine learning.
DeepWalk Paper: https://arxiv.org/abs/1403.6652
โพโพโพโพโพโพโพโพโพโพโพโพโพโพโพโพโพ
๐ Programming Books & Merch ๐
๐ The Python Bible Book: https://www.neuralnine.com/books/โฆ
DeepWalk Paper: https://arxiv.org/abs/1403.6652
โพโพโพโพโพโพโพโพโพโพโพโพโพโพโพโพโพ
๐ Programming Books & Merch ๐
๐ The Python Bible Book: https://www.neuralnine.com/books/โฆ
๐5
๐ Machine Learning with Graphs: Applications of Deep Graph Generation.
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #DGNN #GNN
๐ฅFree recorded course by Jure Leskovec, Computer Science, PhD
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #Machine_Learning #DGNN #GNN
YouTube
Stanford CS224W: ML with Graphs | 2021 | Lecture 15.4 - Applications of Deep Graph Generation
For more information about Stanfordโs Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3EwmakW
Lecture 15.4: Application of Deep Graph Generative Models to Molecule Generation
Jure Leskovec
Computer Science, PhD
Finallyโฆ
Lecture 15.4: Application of Deep Graph Generative Models to Molecule Generation
Jure Leskovec
Computer Science, PhD
Finallyโฆ
๐1
๐ Machine Learning with Graphs - Node Embeddings
๐ฅSDML is partnering with Houston Machine Learning on a series about machine learning with graphs.
๐ฝ Watch
๐ฑChannel: @ComplexNetworkAnalysis
#video #Machine_Learning #Graph #Node_Embedding
๐ฅSDML is partnering with Houston Machine Learning on a series about machine learning with graphs.
๐ฝ Watch
๐ฑChannel: @ComplexNetworkAnalysis
#video #Machine_Learning #Graph #Node_Embedding
YouTube
Machine Learning with Graphs - Node Embeddings
SDML is partnering with Houston Machine Learning on a series about machine learning with graphs. The content will be mainly based on the Stanford course: https://web.stanford.edu/class/cs224w/
Series schedule:
Introduction; Machine Learning for Graphs
Traditionalโฆ
Series schedule:
Introduction; Machine Learning for Graphs
Traditionalโฆ
๐3๐2
๐Graph-Based Data Science, Machine Learning, and AI
๐ฅTechnical Paper
๐ Study
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Graph #AI #Data_Science #Machine_Learning
๐ฅTechnical Paper
๐ Study
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Graph #AI #Data_Science #Machine_Learning
DZone
Graph-Based Data Science, Machine Learning, and AI
What does graphing have to do with machine learning and data science? A lot, actually โ learn more in The Year of the Graph Newsletter's Spring 2021 edition.
โค3๐2
๐ Machine Learning with Graphs: Graph Neural Networks in Computational Biology
๐ฅFree recorded course by Prof. Marinka Zitnik
๐ฅIn this lecture, Prof. Marinka gives an overview of why graph learning techniques can greatly help with computational biology research. Concretely, this talk covers 3 exemplar use cases: (1) Discovering safe drug-drug combinations via multi-relational link prediction on heterogenous knowledge graphs; (2) Classify patient outcomes and diseases via learning subgraph embeddings; and (3) Learning effective disease treatments through few-shot learning for graphs.
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #GNN #Machine_Learning #computational_biology
๐ฅFree recorded course by Prof. Marinka Zitnik
๐ฅIn this lecture, Prof. Marinka gives an overview of why graph learning techniques can greatly help with computational biology research. Concretely, this talk covers 3 exemplar use cases: (1) Discovering safe drug-drug combinations via multi-relational link prediction on heterogenous knowledge graphs; (2) Classify patient outcomes and diseases via learning subgraph embeddings; and (3) Learning effective disease treatments through few-shot learning for graphs.
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #GNN #Machine_Learning #computational_biology
YouTube
Stanford CS224W: Machine Learning with Graphs | 2021 | Lecture 18 - GNNs in Computational Biology
For more information about Stanfordโs Artificial Intelligence professional and graduate programs, visit: https://stanford.io/2XVImFC
Lecture 18 - Graph Neural Networks in Computational Biology
Jure Leskovec
Computer Science, PhD
We are glad to invite Prof.โฆ
Lecture 18 - Graph Neural Networks in Computational Biology
Jure Leskovec
Computer Science, PhD
We are glad to invite Prof.โฆ
๐4๐1
๐ Machine Learning with Graphs: Pre-Training Graph Neural Networks
๐ฅFree recorded course by Prof. Jure Leskovec
๐ฅThere are two challenges in applying GNNs to scientific domains: scarcity of labeled data and out-of-distribution prediction. In this video we discuss methods for pre-training GNNs to resolve these challenges. The key idea is to pre-train both node and graph embeddings, which leads to significant performance gains on downstream tasks.
๐ฝ Watch
๐More details can be found in the paper: Strategies for Pre-training Graph Neural Networks
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #GNN #Machine_Learning
๐ฅFree recorded course by Prof. Jure Leskovec
๐ฅThere are two challenges in applying GNNs to scientific domains: scarcity of labeled data and out-of-distribution prediction. In this video we discuss methods for pre-training GNNs to resolve these challenges. The key idea is to pre-train both node and graph embeddings, which leads to significant performance gains on downstream tasks.
๐ฝ Watch
๐More details can be found in the paper: Strategies for Pre-training Graph Neural Networks
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #GNN #Machine_Learning
arXiv.org
Strategies for Pre-training Graph Neural Networks
Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce...
๐4โค1
๐ A Survey on Machine Learning Solutions for Graph Pattern Extraction
๐ Publish year: 2022
๐งโ๐ปAuthors:Kai Siong Yow, Ningyi Liao, Siqiang Luo, Reynold Cheng, Chenhao Ma, Xiaolin Han
๐ขUniversity: g, Nanyang Technological University
๐บ China, Singapore
๐ Study the paper
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Survey #Machine_learning #Pattern
๐ Publish year: 2022
๐งโ๐ปAuthors:Kai Siong Yow, Ningyi Liao, Siqiang Luo, Reynold Cheng, Chenhao Ma, Xiaolin Han
๐ขUniversity: g, Nanyang Technological University
๐บ China, Singapore
๐ Study the paper
๐ฒChannel: @ComplexNetworkAnalysis
#paper #Survey #Machine_learning #Pattern
๐2๐2
๐ Machine Learning for Graph Algorithms and Representations
๐A Thesis Submitted to the Faculty in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Engineering Sciences
๐Publish year: 2024
๐งโ๐ปAuthor: Allison Mann
๐ขUniversity: College Hanover, New Hampshire
๐Study Thesis
๐ฑChannel: @ComplexNetworkAnalysis
#Thesis #Machine_Learning #Algorithms #Representations
๐A Thesis Submitted to the Faculty in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Engineering Sciences
๐Publish year: 2024
๐งโ๐ปAuthor: Allison Mann
๐ขUniversity: College Hanover, New Hampshire
๐Study Thesis
๐ฑChannel: @ComplexNetworkAnalysis
#Thesis #Machine_Learning #Algorithms #Representations
๐1
๐Community detection in social networks using machine learning: a systematic mapping study
๐ Publish year: 2024
๐Journal: Knowledge and Information Systems (I.F=2.5)
๐งโ๐ปAuthors: Mahsa Nooribakhsh, Marta Fernรกndez-Diego, Fernando Gonzรกlez-Ladrรณn-De-Guevara. Mahdi Mollamotalebi
๐ขUniversity: Universitat Politรจcnica de Valรจncia, Camino de Vera, s/n, 46022, Valencia, Spain and Islamic Azad University, Qazvin, Iran
๐ Study paper
๐ฑChannel: @ComplexNetworkAnalysis
#paper #Community_detection #Machine_learning #mapping
๐ Publish year: 2024
๐Journal: Knowledge and Information Systems (I.F=2.5)
๐งโ๐ปAuthors: Mahsa Nooribakhsh, Marta Fernรกndez-Diego, Fernando Gonzรกlez-Ladrรณn-De-Guevara. Mahdi Mollamotalebi
๐ขUniversity: Universitat Politรจcnica de Valรจncia, Camino de Vera, s/n, 46022, Valencia, Spain and Islamic Azad University, Qazvin, Iran
๐ Study paper
๐ฑChannel: @ComplexNetworkAnalysis
#paper #Community_detection #Machine_learning #mapping
๐Graph Data Science and machine learning applications
๐Master Degree Thesis by Antonella Cardillo form POLITECNICO DI TORINO
๐Publish year: 2024
๐ Study thesis
๐ฒChannel: @ComplexNetworkAnalysis
#thesis #Graph #machine_learning #Data_Science
๐Master Degree Thesis by Antonella Cardillo form POLITECNICO DI TORINO
๐Publish year: 2024
๐ Study thesis
๐ฒChannel: @ComplexNetworkAnalysis
#thesis #Graph #machine_learning #Data_Science
๐2๐ฏ1
๐ Machine Learning with Graphs: hyperbolic graph embeddings
๐ฅFree recorded course by Prof. Jure Leskovec
๐ฅ This part focused on graph representation learning in Euclidean embedding spaces. In this lecture, we introduce hyperbolic embedding spaces, which are great for modeling hierarchical, tree-like graphs. Moreover, we introduce basics for hyperbolic geometry models, which leads to the idea of hyperbolic GNNs. More details can be found in the paper: Hyperbolic Graph Convolutional Neural Networks
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #GNN #Machine_Learning
๐ฅFree recorded course by Prof. Jure Leskovec
๐ฅ This part focused on graph representation learning in Euclidean embedding spaces. In this lecture, we introduce hyperbolic embedding spaces, which are great for modeling hierarchical, tree-like graphs. Moreover, we introduce basics for hyperbolic geometry models, which leads to the idea of hyperbolic GNNs. More details can be found in the paper: Hyperbolic Graph Convolutional Neural Networks
๐ฝ Watch
๐ฒChannel: @ComplexNetworkAnalysis
#video #course #Graph #GNN #Machine_Learning
YouTube
Stanford CS224W: Machine Learning with Graphs | 2021 | Lecture 19.2 - Hyperbolic Graph Embeddings
For more information about Stanfordโs Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3Brc7vN
Jure Leskovec
Computer Science, PhD
In previous lectures, we focused on graph representation learning in Euclidean embeddingโฆ
Jure Leskovec
Computer Science, PhD
In previous lectures, we focused on graph representation learning in Euclidean embeddingโฆ
๐2