3-0-0 [3]
700 Level
Tue, Thu 8:00AM - 8:50AM
Fri 5:00PM - 5:50PM
https://moodle.iitj.ac.in/
Enrollment Code: vy5f9w
Introduction: Complex Systems, Graph Data Structure, Graph Representations, Spectral graph theory, Real world networks and applications.
Graph Representation Learning: Node Embeddings, Graph Convolutional Networks, Design Space, Inductive Representation Learning, Graph Attention Networks, Hierarchical Graph Representation Learning, Graph Embeddings, Over smoothing Issues, Expressiveness of GNN, GNN vs CNN, Graph Representation Learning vs Graph Signal Processing.
GNN Applications: Heterogeneous and Multilayer graphs, Knowledge graphs, Reasoning over knowledge graphs, Graphs and LLMs, Neural subgraph matching, GCN for Recommender Systems, Node Classification, Graph Classification, Community Detection, Link Prediction and Causality.
Large Scale Graphs: Dealing with large graphs, Cluster-GCN, Simplifying Graph Convolutional Networks.
Interactive Activity | Assignments | Group Activity |
10% | 20% | 10% |
Minor | Major | |
20% | 40% |
There will be activities in the LMS or in Classroom where students are provided with different tasks to complete. In many cases we will perform these activities during the class on mobile or laptop. Each of these activity may have different grading rules which will be intemated to you.
There will be 2 to 3 assignments related to course content. The assignments are expected to be completed alone. Students are encouraged to discuss with the fellow mates. The submission in such cases should mention the name and roll no of the people who work together. Best two will be counted for the grading even if we only have 2 assignments during the semester.
This will be a practical project where students will work together for a common goal. There will be demo and Q&A at the end of the semester for evaluation.
Minor and Major exam will be with pen and paper, offline, closed book. The questions will be mixed of objective and subjective.
Plagiarism tolerance is 7% from single source and 15% cumulative, anything more will reduce your marks as follows:
These policy will apply for any assignments, hands on and practical work. Copying from friends and internet both treated similarly.