MATH - Advanced learning for text and graph data ALTEGRAD

$logo du site institutionnel$

$Version anglaise$

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.

Video de présentation

Logistic 2021 :

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 : https://moodle.lix.polytechnique.fr/moodle/

Schedule 2021 : 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://docs.google.com/forms/d/11ZcoKzVenCEcVtgbxhuJ05CGBb2JrBWbPUoqQ7nOMHc/edit

Course Syllabus 2021-22 :

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
French Lingusitic resources: http://master2-bigdata.polytechnique.fr/FrenchLinguisticResources/

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.