Accès direct au contenu

MATH

Version anglaise

aide

Accueil > Formations > Master MVA > Présentation des cours

Advanced learning for text and graph data ALTEGRAD

Lecturer : Michalis Vazirgiannis (Polytechnique)

Introduction :

The ALTEGRAD course aims at providing an overview of state-of-the-art ML and AI methods for text and graph data with a significant focus on applications.

Vidéo de Présentation

Logistic 2020 :

7 sessions of 4 hours : Each session = two hours of lecture followed by two hours of programming sessions.

Evaluation : Grading for the course will be based on a final data challenge plus lab based evaluation :

  • 20% lab assignments
  • 80% data challenge performance (report/creativity/leaderboard score/)

Course web page / moodle : http://moodle.lix.polytechnique.fr

Schedule 2020 : always 14:00 - 18:00 / Synchronous video classes (most likely zoom)

  • 17, 24 Nov 2020
  • 1,8, 15 Dec 2020
  • 12, 19 Jan 2021

Mandatory registration :

In order to
  • get access to the teaching / lab material
  • Receive our announcements
all interested students must enroll and fill the following form at https://tinyurl.com/ycsp2wcs
 

Course Syllabus 2020-21 :


1.1 TEXT/NLP - Graph based Text Mining
  •  Graph-of-words  GoWvis 
  • Keyword extraction (TFIDF, TextRank, ECIR'15, EMNLP'16)
  •  extractive summarization (EMNLP'17) 
  • Sub-event detection in twitter streams (ICWSM'17)  
  • graph based document classification: TW-IDF (ASONAM'15), TW-ICW, subgraphs (ACL'15)
  • abstractive summarization - ACL 2018 summarization
1.2 TEXT - NLP - Word & doc embeddings (P)
  • Word embeddings: word2vec-glove models,  doc2vec, subword, Latent Semantic Indexing, context based embeddings  
  • doc similarity metrics: Word Mover's distance, shortest path kernels (EMNLP16)

1.3 Deep learning for NLP

  • CNNs, RNNs LSTMs for NLP, text classification
  • Meta-architectures
  • Sequence to Sequence: Attention (HAN), 
    • Domains: summarization.
    • Translation, image captioning
  • Unsupervised word sense detection/disambiguation

1.4 Graph kernels, community detection

Grakel python library:  https://github.com/ysig/GraKeL/

1.5 Deep Learning for Graphs - node classification

  • node embeddings (deepwalk & node2vec) for node classification and link prediction  

  • Supervised node embeddings (GCNN, ...)
1.6 Deep Learning for Graphs - Graph classification 
  • graph CNNs

  • message passing
  • Graph - Auto-encoders

1.7 Sets embeddings - point clouds

1.8 Network Architecture Search - interpretability.