Numpy: [User manual] [Reference manual]
Pandas: [Zipped documentation]
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]
2. Lab 2 - Implement pageRank algorithm without and with teleportation
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
5. Lab 5 - ML model training on graph data with CE, SCL losses, etc.
6. Lab 6 - Graph Encoder-decoder model -1 (Matrix factorization, Random Walk)
7. Lab 7: Graph Encoder-decoder model -2 (RESCAL)
8. Lab 8: Vanilla GCN Implementation
X-SAMPLE CONTRASTIVE LOSS: IMPROVING CON TRASTIVE LEARNING WITH SAMPLE SIMILARITY GRAPHS
FlowchartQA: The First Large-Scale Benchmark for Reasoning over Flowcharts
Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs
Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning