Treffer: SINr: a python package to train interpretable word and graph embeddings
Title:
SINr: a python package to train interpretable word and graph embeddings
Authors:
Contributors:
Laboratoire d'Informatique de l'Université du Mans (LIUM), Le Mans Université (UM), Equipe Language and Speech Technology (LST), Le Mans Université (UM)-Le Mans Université (UM), Laboratoire d'Informatique Fondamentale d'Orléans (LIFO), Université d'Orléans (UO)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), ANR-21-CE23-0010,DIGING,Plongements lexicaux temporels et dynamiques basés graphes(2021)
Source:
Book of Abstracts - FRCCS 2023. ; French Regional Conference on Complex Systems ; https://hal.science/hal-04113024 ; French Regional Conference on Complex Systems, May 2023, Le Havre, France. pp.215, ⟨10.5281/zenodo.7957531⟩ ; https://iutdijon.u-bourgogne.fr/ccs-france/
Publisher Information:
CCSD
Publication Year:
2023
Collection:
Le Mans Université: Archives Ouvertes (HAL)
Subject Terms:
Graph embedding, Word embedding, Interpretability, Frugal machine learning, Plongements de graphes, Plongements lexicaux, Interprétabilité, Aprentissage Automatique Frugal, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO]Computer Science [cs], [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS]
Document Type:
Konferenz
conference object
Language:
English
DOI:
10.5281/zenodo.7957531
Availability:
Rights:
http://creativecommons.org/licenses/by/ ; info:eu-repo/semantics/OpenAccess
Accession Number:
edsbas.C0F6D353
Database:
BASE
Weitere Informationen
International audience ; In this paper, we introduce the SINr Python package to train word and graph embeddings. The SINr approach is based on community detection: a vector for a node is built upon the distribution of its connections through the communities detected on the graph at hand. Because of this, the algorithm runs very fast, and does not require GPUs to proceed. Furthermore, the dimensions of the embedding space are interpretable, those are based on the communities extracted. The package is distributed under Cecill-2.1 license and is available on Github and pypi.