@inproceedings{vargas-vieyra-etal-2020-joint,
title = "Joint Learning of the Graph and the Data Representation for Graph-Based Semi-Supervised Learning",
author = "Vargas-Vieyra, Mariana and
Bellet, Aur{\'e}lien and
Denis, Pascal",
editor = "Ustalov, Dmitry and
Somasundaran, Swapna and
Panchenko, Alexander and
Malliaros, Fragkiskos D. and
Hulpu{\textcommabelow{s}}, Ioana and
Jansen, Peter and
Jana, Abhik",
booktitle = "Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.textgraphs-1.4",
doi = "10.18653/v1/2020.textgraphs-1.4",
pages = "35--45",
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 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.",
}