Main lectures provided in CentraleSupelec engineer programme and Paris-Saclay Master 2 programme

• Models and systems for Big Data Management
  • From Relational foundations to NoSQL databases: key-value (Redis), columnar (Apache Parquet), document(MongoDB), graph (Neo4J)
• Parallel Computing Model & Distributed environment
  • MapReduce Model, Implementation in Spark & Resilient Distributed Data
  • Pregel computation model for distributed graphs - Spark & GraphX
• Network Science
  • Centrality metrics, Random Walk, PageRank, Community Detection (Louvain, and graph topology-based heuristics) & Influence Maximisation
• Graph Machine Learning: Clustering & Node Classification & Link Prediction
  • Shallow Graph Embedding: Spectral approaches, Laplacian Eigenmap, unsupervised random walk-based approaches (Node2Vec, DeepWalk)
  • Deep Embedding Approaches: GNN, RGCN, GraphSAGE, GAT, ...
  • Translational Embedding Approaches TransE, TransH, TranR, ...