Assignments & Labs

Documentations:

• Numpy: [User manual] [Reference manual] 

• Pandas: [Zipped documentation]

• Pytorch: PyTorch documentation — PyTorch 2.9 documentation 

Lab assignments

1. Lab 1[A] - Introduction to Python and Numpy [ To be done by students on their own]

   • Lab sheet:  Jupyter Notebook 

   • Solution:  Lab1[A]

    Lab 1[B] - Introduction to networkx [To be done during Lab session]

• Lab Sheet: Lab1

• Documentation: networkX

• Solution: Lab1[B] 

2. Lab 2 - Implement pageRank algorithm without and with teleportation

• Lab Sheet: Lab2

• Solution: Lab2

3. Lab 3 - Dimensionality reduction using PCA, Laplacian eigenmaps, and Spectral clustering

• Lab Sheet: Lab3, Jupyter_Notebook

• Solution: Lab3

4. Lab 4 - Label propagation and Label spreading 

• Lab Sheet: Lab4

• Solution: Lab4

5. Lab 5 - ML model training on graph data with CE, SCL losses, etc.

• Lab Sheet: Lab5

• Solution: Lab5

6. Lab 6 - Graph Encoder-decoder model -1 (Matrix factorization, Random Walk)

• Lab Sheet: Lab6

• Solution : Lab6

7. Lab 7: Graph Encoder-decoder model -2 (RESCAL)

• Lab sheet: Lab7

• Solution:  Lab 7

8. Lab 8: Vanilla GCN Implementation

• Lab Sheet: Lab8

• Solution: Lab8

Research papers for Project work reference:

1. X-SAMPLE CONTRASTIVE LOSS: IMPROVING CON TRASTIVE LEARNING WITH SAMPLE SIMILARITY GRAPHS 

2. FlowchartQA: The First Large-Scale Benchmark for Reasoning over Flowcharts 

3. Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs 

4. STRATEGIES FOR PRE-TRAINING GRAPH NEURAL NETWORKS 

5. Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning 

Lab Attendance