Ce diaporama a bien été signalé.
Nous utilisons votre profil LinkedIn et vos données d’activité pour vous proposer des publicités personnalisées et pertinentes. Vous pouvez changer vos préférences de publicités à tout moment.
The
magic
world of
Graph ML
What are graphs?
Nodes Edges
50 shades of graphs
Simplifying assumption:
• Undirected
• Self-edges
What we care about: features
Classic node features example: Cora
• Vocab
• Is word present in this paper/node?
Edge featur...
Graph Neural Networks (GNNs) Abstract applications:
• Graph classification/regression
• Node/edge classification/regression
Graph ML - applications
Graph ML apps
Graph ML apps – fundamental science
Contrasting Graph ML with CV, NLP, RL
Graph ML – high level survey
Graph embedding methods
DeepWalk, Node2Vec, etc.
Convolution (on the way from CV to Graph ML)
Adjacency matrix, Laplacian, signals
GNNs – spectral methods
Cons:
• Computationally expensive ~O(n³)
• Inherently transductive
Pros:
• Mathematical notion of ...
Spatial GNNs
GNN expressivity (going beyond WL)
One solution: counting subgraphs
Are these graphs the same?
More expressive -> better f...
Dynamic graphs
• Representing time as a vector
• Temporal neighborhood
GAT project
GAT – Graph Attention Network project
Graph Attention Network (GAT) project
Further learning resources for Graph ML:
• https://github.com/gordicaleksa/pytorch-GAT (Graph Attention Net)
• https://www...
How to get started with Graph Machine Learning
Prochain SlideShare
Chargement dans…5
×

0

Partager

Télécharger pour lire hors ligne

How to get started with Graph Machine Learning

Télécharger pour lire hors ligne

A talk by Aleksa Gordic | Software - Deep Learning engineer, Microsoft | The AI Epiphany

What can you learn about Graph Machine Learning in 2 months?

Aleksa Gordic, Machine Learning engineer @ Microsoft and Founder @ The AI Epiphany, shares his journey in the world of Graph Machine Learning. Aleksa started exploring the basics in the world of Graph Machine Learning, and ended up implementing and open sourcing his own Graph Attention Network on PyTorch.

In this talk, Aleksa will share the fundamentals of Graph Machine Learning, provide real-world examples, resources, and everything his younger self would be grateful for. Aleksa will also be available to answer questions.

What is Graph Machine Learning? Simply put, Graph Machine Learning is a branch of machine learning that deals with graph data.

Graphs consist of nodes, that may have feature vectors associated with them, and edges, which again may or may not have feature vectors attached. The applications are endless. Massive-scale recommender systems, particle physics, computational pharmacology / chemistry / biology, traffic prediction, fake news detection, and the list goes on and on.

  • Soyez le premier à aimer ceci

How to get started with Graph Machine Learning

  1. 1. The magic world of Graph ML
  2. 2. What are graphs? Nodes Edges
  3. 3. 50 shades of graphs Simplifying assumption: • Undirected • Self-edges
  4. 4. What we care about: features Classic node features example: Cora • Vocab • Is word present in this paper/node? Edge features example: molecules
  5. 5. Graph Neural Networks (GNNs) Abstract applications: • Graph classification/regression • Node/edge classification/regression
  6. 6. Graph ML - applications
  7. 7. Graph ML apps
  8. 8. Graph ML apps – fundamental science
  9. 9. Contrasting Graph ML with CV, NLP, RL
  10. 10. Graph ML – high level survey
  11. 11. Graph embedding methods DeepWalk, Node2Vec, etc.
  12. 12. Convolution (on the way from CV to Graph ML)
  13. 13. Adjacency matrix, Laplacian, signals
  14. 14. GNNs – spectral methods Cons: • Computationally expensive ~O(n³) • Inherently transductive Pros: • Mathematical notion of convolution Chebnets: k-hop, faster
  15. 15. Spatial GNNs
  16. 16. GNN expressivity (going beyond WL) One solution: counting subgraphs Are these graphs the same? More expressive -> better for your problem? No.
  17. 17. Dynamic graphs • Representing time as a vector • Temporal neighborhood
  18. 18. GAT project
  19. 19. GAT – Graph Attention Network project
  20. 20. Graph Attention Network (GAT) project
  21. 21. Further learning resources for Graph ML: • https://github.com/gordicaleksa/pytorch-GAT (Graph Attention Net) • https://www.youtube.com/c/TheAIEpiphany (lots of Graph ML vids) • https://gordicaleksa.medium.com/how-to-get-started-with-graph- machine-learning-afa53f6f963a (getting started with Graph ML)

A talk by Aleksa Gordic | Software - Deep Learning engineer, Microsoft | The AI Epiphany What can you learn about Graph Machine Learning in 2 months? Aleksa Gordic, Machine Learning engineer @ Microsoft and Founder @ The AI Epiphany, shares his journey in the world of Graph Machine Learning. Aleksa started exploring the basics in the world of Graph Machine Learning, and ended up implementing and open sourcing his own Graph Attention Network on PyTorch. In this talk, Aleksa will share the fundamentals of Graph Machine Learning, provide real-world examples, resources, and everything his younger self would be grateful for. Aleksa will also be available to answer questions. What is Graph Machine Learning? Simply put, Graph Machine Learning is a branch of machine learning that deals with graph data. Graphs consist of nodes, that may have feature vectors associated with them, and edges, which again may or may not have feature vectors attached. The applications are endless. Massive-scale recommender systems, particle physics, computational pharmacology / chemistry / biology, traffic prediction, fake news detection, and the list goes on and on.

Vues

Nombre de vues

122

Sur Slideshare

0

À partir des intégrations

0

Nombre d'intégrations

2

Actions

Téléchargements

1

Partages

0

Commentaires

0

Mentions J'aime

0

×