update lecture notes

Author: SaberPRC

Lecture-notes/Lecture-1-classical-graph-representation/DGL-1-ANNOTATED.pdf renamed to Lecture-notes/DGL_Lecture_1/DGL_Lecture_1_Annotated.pdf

@@ -0,0 +1,8 @@
+### DGL Lecture 1
+***
+
+* [Lecture 1.1](https://www.youtube.com/watch?v=gQRV_jUyaDw&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=1): Graph types
+
+* [Lecture 1.2](https://www.youtube.com/watch?v=WnQZILX6aC0&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=2): The Graph matrix
+
+* [Lecture 1.3](https://www.youtube.com/watch?v=u4bkPFTsvxY&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=3): Graph learning tasks

Lecture-notes/Lecture-1-classical-graph-representation/DGL-1-CLEAN.pdf renamed to Lecture-notes/DGL_Lecture_1/DGL_Lecture_1_Clean.pdf

@@ -0,0 +1,11 @@
+### DGL Lecture 2
+***
+* [Lecture 2.1](https://www.youtube.com/watch?v=gS1MnemlmFQ&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=4): The logic behind graph-based learning
+
+* [Lecture 2.2](https://www.youtube.com/watch?v=UdCx7mFGYaY&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=5): The evolving landscope of feature embedding
+
+* [Lecture 2.3](https://www.youtube.com/watch?v=feMNrzUUIFc&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=6): Shallow graph node embedding
+
+* [Lecture 2.4](https://www.youtube.com/watch?v=XZtd_4aEFJM&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=7): Analyzing a single GCN layer
+
+* [Lecture 2.5](https://www.youtube.com/watch?v=xiiGb4Y5OPo&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=8): Generalized GCN node and layer updates

Lecture-notes/DGL_Lecture_1/README.md

@@ -0,0 +1,13 @@
+### DGL Lecture 3
+***
+
+
+* [Lecture 3.1](https://www.youtube.com/watch?v=SxEgHgguqkI&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=9): GCN training and loss optimization
+
+* [Lecture 3.2](https://www.youtube.com/watch?v=b8GWuCyEt3Q&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=10): GNN inductive capability & graph-based learning
+
+* [Lecture 3.3](https://www.youtube.com/watch?v=BYC_i-V7Fx8&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=11): Graph pooling & embedding aggregating
+
+* [Lecture 3.4](https://www.youtube.com/watch?v=Kg3P4EaWMBk&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=12): GCN layer operations
+
+* [Lecture 3.5](https://www.youtube.com/watch?v=zRmzVkidkqA&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=13): Global and local aggregation methods

Lecture-notes/Lecture-2-feature-embedding-ML-to-GCN/DGL-2-ANNOTATED.pdf renamed to Lecture-notes/DGL_Lecture_2/DGL_Lecture_2_Annotated.pdf

@@ -0,0 +1,15 @@
+### DGL Lecture 4
+***
+
+
+* [Lecture 4.1](https://www.youtube.com/watch?v=H8RsdeAiOBg&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=14): Point, batch and mini-batch gradient descent
+
+* [Lecture 4.2](https://www.youtube.com/watch?v=704WpxpDaig&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=15): Batching and GNN sampling methods
+
+* [Lecture 4.3](https://www.youtube.com/watch?v=fyBxrWgb44U&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=16): Recap on GNN sampling methods
+
+* [Lecture 4.4](https://www.youtube.com/watch?v=hdMlYbqyzJQ&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=17): GNN batch normalization layer
+
+* [Lecture 4.5](https://www.youtube.com/watch?v=3e5zjVKsbsw&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=18): Generalized GNN layer and Dropout
+
+* [Lecture 4.6](https://www.youtube.com/watch?v=Lrr25EzAgkI&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=19): GNN inductive vs transductive learning

Lecture-notes/DGL_Lecture_2/DGL_Lecture_2_Clean.pdf

@@ -0,0 +1,11 @@
+### DGL Lecture 5
+***
+
+
+* [Lecture 5.1](https://www.youtube.com/watch?v=Ac8h2rvhieU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=20): Node permutation invariance in GNNs
+
+* [Lecture 5.2](https://www.youtube.com/watch?v=9Ko8EN7zVLM&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=21): Node permutation equivariance in GNNs
+
+* [Lecture 5.3](https://www.youtube.com/watch?v=vZ06k7kiUMU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=22): GNN expressiveness
+
+* [Lecture 5.4](https://www.youtube.com/watch?v=trJwayzmEoU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=23): Graph Isomorphism Network Expressive Nets

Lecture-notes/DGL_Lecture_2/README.md

@@ -0,0 +1,18 @@
+### DGL Lecture 6
+***
+
+
+* [Lecture 6.1](https://www.youtube.com/watch?v=TLiHaXinKlA&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=24): Overview of supervised generative GNNs
+
+* [Lecture 6.2](https://www.youtube.com/watch?v=JV-zvTBa9e4&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=25): Self-supervised/unsupervised generative GNNs
+
+* [Lecture 6.3](https://www.youtube.com/watch?v=IQ3SJsJwajU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=26): Unconditional sequential graph generation
+
+* [Lecture 6.4](https://www.youtube.com/watch?v=3YosTx06Nl4&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=27): Unconditional one-shot graph generation
+
+* [Lecture 6.5](https://www.youtube.com/watch?v=I4uquGfm-N8&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=28): Supervised conditional generation on graphs
+
+* [Lecture 6.6](https://www.youtube.com/watch?v=Sp3L1wP1urs&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=29): Generative Graph U-Net
+
+* [Lecture 6.7](https://www.youtube.com/watch?v=7S1Ut6Kx6i8&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=30): Evaluation measures for generative GNNs
+

Lecture-notes/DGL_Lecture_3/DGL_Lecture_3_Annotated.pdf

@@ -1,5 +1,94 @@
-# DGL 2024 (ICL, Computing)
-Deep Graph-Based Learning Course.
+# Deep Graph Learning (DGL, 2024) 
 
-# Lecture videos and notes
-Follow us at https://www.youtube.com/watch?v=gQRV_jUyaDw&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&ab_channel=BASIRALab
+Taught by Prof. [Islem Rekik](https://basira-lab.com/) at Imperial College London
+***
+
+### Introduction
+This repo contains all the lecture notes for this DGL course. All relevant records for this course can be accessed at [BASIRA Lab](https://www.youtube.com/playlist?list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T).
+
+***
+### Course Lectures
+* [Lecture 1](./Lecture-notes/DGL_Lecture_1/):
+
+    * [Lecture 1.1](https://www.youtube.com/watch?v=gQRV_jUyaDw&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=1): Graph types
+
+    * [Lecture 1.2](https://www.youtube.com/watch?v=WnQZILX6aC0&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=2): The Graph matrix
+
+    * [Lecture 1.3](https://www.youtube.com/watch?v=u4bkPFTsvxY&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=3): Graph learning tasks
+
+* [Lecture 2](./Lecture-notes/DGL_Lecture_2/):
+    
+    * [Lecture 2.1](https://www.youtube.com/watch?v=gS1MnemlmFQ&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=4): The logic behind graph-based learning
+
+    * [Lecture 2.2](https://www.youtube.com/watch?v=UdCx7mFGYaY&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=5): The evolving landscope of feature embedding
+
+    * [Lecture 2.3](https://www.youtube.com/watch?v=feMNrzUUIFc&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=6): Shallow graph node embedding
+
+    * [Lecture 2.4](https://www.youtube.com/watch?v=XZtd_4aEFJM&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=7): Analyzing a single GCN layer
+
+    * [Lecture 2.5](https://www.youtube.com/watch?v=xiiGb4Y5OPo&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=8): Generalized GCN node and layer updates
+
+* [Lecture 3](./Lecture-notes/DGL_Lecture_3/):
+
+    * [Lecture 3.1](https://www.youtube.com/watch?v=SxEgHgguqkI&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=9): GCN training and loss optimization
+
+    * [Lecture 3.2](https://www.youtube.com/watch?v=b8GWuCyEt3Q&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=10): GNN inductive capability & graph-based learning
+
+    * [Lecture 3.3](https://www.youtube.com/watch?v=BYC_i-V7Fx8&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=11): Graph pooling & embedding aggregating
+
+    * [Lecture 3.4](https://www.youtube.com/watch?v=Kg3P4EaWMBk&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=12): GCN layer operations
+
+    * [Lecture 3.5](https://www.youtube.com/watch?v=zRmzVkidkqA&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=13): Global and local aggregation methods
+
+* [Lecture 4](./Lecture-notes/DGL_Lecture_4/):
+
+    * [Lecture 4.1](https://www.youtube.com/watch?v=H8RsdeAiOBg&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=14): Point, batch and mini-batch gradient descent
+
+    * [Lecture 4.2](https://www.youtube.com/watch?v=704WpxpDaig&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=15): Batching and GNN sampling methods
+
+    * [Lecture 4.3](https://www.youtube.com/watch?v=fyBxrWgb44U&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=16): Recap on GNN sampling methods
+
+    * [Lecture 4.4](https://www.youtube.com/watch?v=hdMlYbqyzJQ&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=17): GNN batch normalization layer
+
+    * [Lecture 4.5](https://www.youtube.com/watch?v=3e5zjVKsbsw&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=18): Generalized GNN layer and Dropout
+
+    * [Lecture 4.6](https://www.youtube.com/watch?v=Lrr25EzAgkI&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=19): GNN inductive vs transductive learning
+
+* [Lecture 5](./Lecture-notes/DGL_Lecture_5/):
+
+    * [Lecture 5.1](https://www.youtube.com/watch?v=Ac8h2rvhieU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=20): Node permutation invariance in GNNs
+
+    * [Lecture 5.2](https://www.youtube.com/watch?v=9Ko8EN7zVLM&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=21): Node permutation equivariance in GNNs
+
+    * [Lecture 5.3](https://www.youtube.com/watch?v=vZ06k7kiUMU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=22): GNN expressiveness
+
+    * [Lecture 5.4](https://www.youtube.com/watch?v=trJwayzmEoU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=23): Graph Isomorphism Network Expressive Nets
+
+* [Lecture 6](./Lecture-notes/DGL_Lecture_6/):
+
+    * [Lecture 6.1](https://www.youtube.com/watch?v=TLiHaXinKlA&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=24): Overview of supervised generative GNNs
+
+    * [Lecture 6.2](https://www.youtube.com/watch?v=JV-zvTBa9e4&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=25): Self-supervised/unsupervised generative GNNs
+
+    * [Lecture 6.3](https://www.youtube.com/watch?v=IQ3SJsJwajU&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=26): Unconditional sequential graph generation
+
+    * [Lecture 6.4](https://www.youtube.com/watch?v=3YosTx06Nl4&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=27): Unconditional one-shot graph generation
+
+    * [Lecture 6.5](https://www.youtube.com/watch?v=I4uquGfm-N8&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=28): Supervised conditional generation on graphs
+
+    * [Lecture 6.6](https://www.youtube.com/watch?v=Sp3L1wP1urs&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=29): Generative Graph U-Net
+
+    * [Lecture 6.7](https://www.youtube.com/watch?v=7S1Ut6Kx6i8&list=PLug43ldmRSo14Y_vt7S6vanPGh-JpHR7T&index=30): Evaluation measures for generative GNNs
+
+***
+### Homeworks
+
+***
+### Paper analysis worksheets
+
+***
+### Project
+
+***
+### Tutorials
+***