Graph Neural Networks: Theory, codes and simulations for AI
What you'll learn
- Fundamentals Graph AI using Internet of Behaviors
- Basics and implementation of Graph Neural Networks
- How to a create a Graph Neural Network, its training, optimization and testing
- AI Graph feature learning and prediction using FastGCN, gated and mixed grain architectures.
- How to derive an AI sub- graph from Graph Neural Networks
- How create a Graph AI model?
- No prior experience in programming is required. You will learn everything you need to know from the very basics
Graph AI carries immense potential for us to explore, connect the dots and build intelligent applications using the Internet of Behaviors (IoB). Many Graph Neural Networks achieved state-of-the-art results on both node and graph classification tasks. However, despite GNNs revolutionizing graph representation learning, there is limited understanding of their area to the students. The purpose of this course is to unfold the basics to the cutting-edge concepts and technologies in this realm.
Graphs are all around us; real-world objects are often defined in terms of their connections to other things. A set of objects, and the connections between them, are naturally expressed as a Graph Neural Network (GCN). Recent developments have increased their capabilities and expressive power. They have profound applications in the realm of AI, fake news detection, traffic prediction to recommendation systems.
This course explores and explains modern AI graph neural networks. In this course, we look at what kind of data is most naturally phrased as a graph, and some common examples. Then we explore what makes graphs different from other types of data, and some of the specialized choices we have to make when using graphs. We then build a modern GNN, walking through each of the parts of the model and gradually to state-of-the-art AI GNN models. Finally, we provide a GNN playground where you can play around with a real-world task and dataset to build a stronger intuition of how each component of an AI GNN model contributes to the predictions it makes.
The topics of this course include:
1. Introduction to Graph Machine Learning.
2. Internet of Behaviors.
3. Homographic Intelligence.
4. Graphs Basics and Eigen Centrality.
4. Graph Neural Networks.
5. Graph Attention Networks.
6. Building a Graph Neural Network
7. GNNs Predictors by Pooling Information.
8. Graph AI and its code implementations in Python.
9. Multi- Graphs and Hyper- Graphs in AI using IoB.
10. Design Space for a GNNs.
11. Inductive Biases in GNNs.
12. Pytorch Geometric Implementations.
13. Node2Vec Feature Learning.
14. FAST GCNs.
15. Gated Graph RNNs.
16. Graph LSTMs
17. Mixed Grain Aggregators.
18. Multimodal Graph AI.
19. 100+ Resources on Graph Neural Networks
Who this course is for:
- Beginner and intermediate learners in data science, machine learning and artificial intelligence
- Research Students in the realm of data science, big data analytics, Neural Networks and Artificial Intelligence
Prof. Dr. Engr. Junaid Zafar is currently working as Chairperson in Department of Electrical and Computer Engineering, Government College University, Lahore. He is also Director, Office of Research, innovation and Commercialization. He has completed his PhD in Electrical and Electronics Engineering, The University of Manchester University, UK, and BSc in Electrical Engineering from U.E.T Lahore. He is Academic visitor to the University of Cambridge, UK, MMU, UK and National University of Ireland. He remained Dual Degree programme coordinator at the Lancaster University, UK. Dr. Engr. Junaid Zafar received Roll of Honors for National Education Commission and Outstanding Teacher/ Researcher Awards from the Higher Education Commission, Pakistan. He is leading the macine learning and Artificial Intelligence centre with GC University, Lahore. He is member of Universal Association of Electronics & Computer Engineers, International Association of Computer Science & Information, and member of International Association of Engineers, IAENG Society of Artificial Intelligence, IAENG Society of Electrical Engineering, Science & Engineering Institute, IAENG Society of Imaging Engineering, Institute of Research Engineers & Doctors, and IAENG Society of Wireless Networks. He is member of editorial board in Journal of Future Technologies & Communications, Technical Programme committee, Frontiers of Information & Technologies, and Technical Programme Committee, Multi- Conference on Sciences & Technology. He is also serving as reviewer for IEEE Transactions on Microwave Theory & Techniques, IEEE Transactions on Antennas, IEEE Antenna & Wireless Propagation Letters, IEEE Transactions on Plasma Science, IEEE Transactions on Magnetics, International Journal of Electronics, and IET Antennas & Radio- wave Propagation. He has so far taught over twenty diffrent online courses based on outcome based student oriented models. He has also supervised more than 100 Masters/ MPhil thesis. He has published over 50 high impact factor publications and presented his work at several national and international renowned platforms.