Skip to Main content Skip to Navigation
Conference papers

Joint Learning of the Graph and the Data Representation for Graph-Based Semi-Supervised Learning

Mariana Vargas-Vieyra 1 Aurélien Bellet 1 Pascal Denis 1
1 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Graph-based semi-supervised learning is appealing when labels are scarce but large amounts of unlabeled data are available. These methods typically use a heuristic strategy to construct the graph based on some fixed data representation, independently of the available labels. In this paper, we propose to jointly learn a data representation and a graph from both labeled and unlabeled data such that (i) the learned representation indirectly encodes the label information injected into the graph, and (ii) the graph provides a smooth topology with respect to the transformed data. Plugging the resulting graph and representation into existing graph-based semi-supervised learning algorithms like label spreading and graph convolutional networks, we show that our approach outperforms standard graph construction methods on both synthetic data and real datasets.
Complete list of metadata
Contributor : Aurélien Bellet Connect in order to contact the contributor
Submitted on : Wednesday, January 6, 2021 - 2:24:10 PM
Last modification on : Thursday, January 20, 2022 - 5:28:57 PM
Long-term archiving on: : Wednesday, April 7, 2021 - 8:18:10 PM


Files produced by the author(s)


  • HAL Id : hal-03100039, version 1


Mariana Vargas-Vieyra, Aurélien Bellet, Pascal Denis. Joint Learning of the Graph and the Data Representation for Graph-Based Semi-Supervised Learning. 14th Workshop on Graph-Based Natural Language Processing (TextGraphs 2020), 2020, Virtual, Spain. ⟨hal-03100039⟩



Les métriques sont temporairement indisponibles