DOS SANTOS Ludovic
Supervision : Patrick GALLINARI
Co-supervision : PIWOWARSKI Benjamin
Representation Learning for Relational Data
First, we proposeda model for heterogeneous graph node classification. Contrary to other state of the art models, our solution is able to learn edge weights when learning simultaneously the representations and the classifiers. To handle the incertainty of the entity representation, we have got interested in using gaussian representations. First of all, we extended our first model, then, we proposed an algorithm for relational time series forecasting where the observations are not only correlated inside each series, but also across the different series.
At last, we apply the Gaussian representation learning approach to the collaborative filtering task.
This is a preliminary work to see if the properties of Gaussian representations found on the two previous tasks were also verified for the ranking one.
The goal of this work was then to generalize the approach to more relational data and not only bipartite graphs between users and items.
Thus, we used gaussian representations for collaborative filtering, and showed their benefits from a theoretical and experimental point of view.
Defence : 12/13/2017
Jury members :
M. Rémi Gilleron, Professeur, Université Lille 3 – Lille - France [Rapporteur]
M. Thierry Artières, Professeur, Université d'Aix Marseille – Marseille - France [Rapporteur]
M. Younès Bennani, Professeur, Université Paris 13 – Paris - France
Mme. Marie-Jeanne Lesot, Maître de conférence, LIP6 - Paris - France
M. Benjamin Piwowarski, Chargé de recherche, LIP6- Paris - France
M. Patrick Gallinari, Professeur, LIP6- Paris - France
- L. DOS SANTOS, B. Piwowarski, L. Denoyer, P. Gallinari : “Representation Learning for Classification in Heterogeneous Graphs with Application to Social Networks”, ACM Transactions on Knowledge Discovery from Data (TKDD), vol. 12 (5), pp. 1-33, (ACM) (2018)
- L. Dos Santos : “Representation Learning for Relational Data”, thesis, defence 12/13/2017, supervision Gallinari, Patrick, co-supervision : Piwowarski, Benjamin (2017)
- L. DOS SANTOS, B. Piwowarski, P. Gallinari : “Gaussian Embeddings for Collaborative Filtering”, Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Tokyo, Japan, pp. 1065-1068, (ACM) (2017)
- L. DOS SANTOS, B. Piwowarski, P. Gallinari : “Multilabel classification on heterogeneous graphs with gaussian embeddings”, ECML-PKDD 2016, Riva del garda, Italy (2016)
- L. DOS SANTOS, B. Piwowarski, P. Gallinari : “Graph Based Method Approach to the ImageCLEF2015 Task1 - Image Annotation”, Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015., vol. 1391, CEUR Workshop Proceedings, Toulouse, France, (CEUR-WS.org) (2015)