Assignments in Machine Learning for Graphs and Sequential Data

PLEASE SEE DOCUMENTED AND COMMENTED CODE IN JUPYTER NOTEBOOKS IN RESPECTIVE SUBFOLDER.

This lecture is build up on the Machine Learning lecture held by Prof. Stephan Günnemann from the Data Analytics and Machine Learning group at TUM. This is considered to be an Advanced ML course that is suited for students who succesfully completed the challenging Machine Learning course at TUM.

Content

Taken from the course description by the Data Analytics and Machine Learning Group at TUM [1].

Introduction

• Machine Learning, Data Mining Process
• Basic Terminology

Scalability

• Similarity Estimation
• Filter-Refine Paradigm
• Hashing & Sketches
• Min-Hashing
• Locality Sensitive Hashing
• Membership Test / Bloom Filter
• Large-Scale Optimization

Temporal Data & Sequences

• Autoregressive Models
• HMMs
• Embeddings (e.g. Word2Vec)
• Neural Networks (e.g. RNN, LSTM)

Graphs & Networks

• Laws, Patterns
• (Deep) Generative Models
• VAE, Implicit Models
• Generative Models for Graphs
• Spectral Methods
• Ranking (e.g., PageRank, HITS)
• Community Detection
• Representation Learning for Graphs
• Graph Neural Networks
• (Unsupervised) Node Embeddings

References

[1] Course description for Machine Learning for Graphs and Sequential Data