{"department":[{"_id":"34"},{"_id":"820"}],"publisher":"European Language Resources Association","type":"conference","citation":{"short":"T. Igamberdiev, I. Habernal, in: Proceedings of the Thirteenth Language Resources and Evaluation Conference, European Language Resources Association, Marseille, France, 2022, pp. 338–350.","bibtex":"@inproceedings{Igamberdiev_Habernal_2022, place={Marseille, France}, title={Privacy-Preserving Graph Convolutional Networks for Text Classification}, booktitle={Proceedings of the Thirteenth Language Resources and Evaluation Conference}, publisher={European Language Resources Association}, author={Igamberdiev, Timour and Habernal, Ivan}, year={2022}, pages={338–350} }","ieee":"T. Igamberdiev and I. Habernal, “Privacy-Preserving Graph Convolutional Networks for Text Classification,” in <i>Proceedings of the Thirteenth Language Resources and Evaluation Conference</i>, 2022, pp. 338–350.","ama":"Igamberdiev T, Habernal I. Privacy-Preserving Graph Convolutional Networks for Text Classification. In: <i>Proceedings of the Thirteenth Language Resources and Evaluation Conference</i>. European Language Resources Association; 2022:338–350.","mla":"Igamberdiev, Timour, and Ivan Habernal. “Privacy-Preserving Graph Convolutional Networks for Text Classification.” <i>Proceedings of the Thirteenth Language Resources and Evaluation Conference</i>, European Language Resources Association, 2022, pp. 338–350.","chicago":"Igamberdiev, Timour, and Ivan Habernal. “Privacy-Preserving Graph Convolutional Networks for Text Classification.” In <i>Proceedings of the Thirteenth Language Resources and Evaluation Conference</i>, 338–350. Marseille, France: European Language Resources Association, 2022.","apa":"Igamberdiev, T., &#38; Habernal, I. (2022). Privacy-Preserving Graph Convolutional Networks for Text Classification. <i>Proceedings of the Thirteenth Language Resources and Evaluation Conference</i>, 338–350."},"author":[{"first_name":"Timour","full_name":"Igamberdiev, Timour","last_name":"Igamberdiev"},{"last_name":"Habernal","full_name":"Habernal, Ivan","first_name":"Ivan","id":"101881"}],"year":"2022","user_id":"15504","date_created":"2023-10-19T08:26:58Z","_id":"48299","status":"public","publication":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","abstract":[{"lang":"eng","text":"Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e.g., citation or social networks. However, sensitive personal information, such as documents with people{’}s profiles or relationships as edges, are prone to privacy leaks, as the trained model might reveal the original input. Although differential privacy (DP) offers a well-founded privacy-preserving framework, GCNs pose theoretical and practical challenges due to their training specifics. We address these challenges by adapting differentially-private gradient-based training to GCNs and conduct experiments using two optimizers on five NLP datasets in two languages. We propose a simple yet efficient method based on random graph splits that not only improves the baseline privacy bounds by a factor of 2.7 while retaining competitive F1 scores, but also provides strong privacy guarantees of epsilon = 1.0. We show that, under certain modeling choices, privacy-preserving GCNs perform up to 90{%} of their non-private variants, while formally guaranteeing strong privacy measures."}],"title":"Privacy-Preserving Graph Convolutional Networks for Text Classification","date_updated":"2023-10-19T12:05:12Z","language":[{"iso":"eng"}],"place":"Marseille, France","page":"338–350"}