Privacy-preserving distributed multi-task learning with asynchronous updates
23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017, Halifax, Kanada, 13 - 17 Ağustos 2017, cilt.Part F129685, ss.1195-1204, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: Part F129685
- Doi Numarası: 10.1145/3097983.3098152
- Basıldığı Şehir: Halifax
- Basıldığı Ülke: Kanada
- Sayfa Sayıları: ss.1195-1204
- Anahtar Kelimeler: Asynchronous proximal optimization, Differential privacy, Multi-task learning
- Boğaziçi Üniversitesi Adresli: Hayır
Özet
Many data mining applications involve a set of related learning tasks. Multi-task learning (MTL) is a learning paradigm that improves generalization performance by transferring knowledge among those tasks. MTL has atracted so much atention in the community and various algorithms have been successfully developed. Recently distributed MTL has also been studied for related tasks whose datais distributed across different geographical regions. One prominent challenge of the distributed MTL frameworks is to maintain the privacy of the data. The distributed data may contain sensitive and private information such as patients' records and registers of a company. In such cases, distributed MTL frameworks are required to preserve the privacy of the data. In this paper, we propose a novel privacy-preserving distributed MTL framework to address this challenge A privacy preserving proximal gradient algorithm, which asynchronously updates models of the learning tasks, is introduced to solve a general class of MTL formulations. The proposed asynchronous approach is robust against network delays and provides a guaranteed differential privacy through carefully designed perturbation. Theoretical guarantees of the proposed algorithm are derived and supported by the extensive experimental results.