%0 Conference Proceedings
%T Joint Learning of the Graph and the Data Representation for Graph-Based Semi-Supervised Learning
%A Vargas-Vieyra, Mariana
%A Bellet, Aurélien
%A Denis, Pascal
%Y Ustalov, Dmitry
%Y Somasundaran, Swapna
%Y Panchenko, Alexander
%Y Malliaros, Fragkiskos D.
%Y Hulpu\textcommabelows, Ioana
%Y Jansen, Peter
%Y Jana, Abhik
%S Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F vargas-vieyra-etal-2020-joint
%X 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 pa- per, 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 learn- ing 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.
%R 10.18653/v1/2020.textgraphs-1.4
%U https://aclanthology.org/2020.textgraphs-1.4
%U https://doi.org/10.18653/v1/2020.textgraphs-1.4
%P 35-45