BÜYÜK VERİLERDE GİZLİLİK TABANLI YAKLAŞIM: FEDERE ÖĞRENME

Year 2019, Volume: 3 Issue: 3, 297 - 304, 31.12.2019

Ahmet Ali Süzen Kiyas Kayaalp

Abstract

Bu çalışmada dağıtık yapılardaki büyük verilerden gizlilik tabanlı makine öğrenmesi uygulamaları geliştirilmesi için federe öğrenme biçimi anlatılmıştır. Federe öğrenme eğitim verilerini yerelde tutarken, cep telefonları ve IoT (Internet of Things) cihazları gibi kaynakları kısıtlı uç aygıtların tahmin için paylaşılan bir model öğrenmesini sağlar. Federe öğrenme büyük ve heterojen ağlarda modellerin istatiksel eğitimlerini içerir. Bu dağıtık yapı içerisinde temel amaç toplam kayıp fonksiyon değerini minimize edebilmektir. Dağıtık yerel cihazlarda modelleri federe öğrenme ile eğitmedeki istatistiksel ve sistematik zorluklar, federe öğrenmenin gerçek dünyaya uygulanmasını zorlaştırmaktadır. Zorlukların çözümü ile ilgili yeni yaklaşımlar ve algoritmalar önerilmektedir. Elde edilen sonuçlar doğrultusunda federe öğrenmenin uygulanması ile merkezi yaklaşım, gizlilik, güvenlik, düzenleyici ve ekonomik olarak faydalar sağlayacağı öngörülmektedir.

Keywords

Federe Öğrenme, Makine Öğrenmesi, Gizlilik, Büyük Veri

A PRIVACY-BASED APPROACH IN BIG DATA: FEDERATED LEARNING

Abstract

This study describes the Federated way of learning to develop privacy-based machine learning applications from large data in distributed structures. Federated learning allows learning a shared model for forecasting resource-restricted end devices, such as mobile phones and IoT (Internet of Things) devices, while keeping training data locally. Federated learning involves statistical training of models in large and heterogeneous networks. The main purpose of this distributed structure is to minimize the total loss function value. The statistical and systematic challenges in federated learning and training in distributed local devices make it difficult to apply federated learning to the real world. It has been proposed new approaches and algorithms for solving challenges. In lights with the results achieved, it is envisaged that the implementation of federated learning and the central approach will bring benefits in terms of privacy, security, regulatory and economic terms.

Keywords

Big Data, Federated Learning, , Machine Learning, Privacy

References

• 1 . Yıldız, A., Endüstri 4.0 ve akıllı fabrikalar. Sakarya University Journal of Science, 22(2), 546-556. 2018. DOI: 10.16984/saufenbilder.321957
• 2 . Lee, J., Bagheri, B., & Kao, H. A., A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing letters, 3, 18-23, 2015.
• 3 . Zhou, K., Liu, T., & Zhou, L., Industry 4.0: Towards future industrial opportunities and challenges. In 2015 12th International conference on fuzzy systems and knowledge discovery (FSKD) 2147-2152. 2015. IEEE.
• 4 . Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., & Kudlur, M, Tensorflow: A system for large-scale machine learning. In 12th {USENIX} Symposium on Operating Systems Design and Implementation, 265-283, 2016.
• 5 . Kayaalp, K., Süzen A.A., Yayın Yeri: IKSAD International Publishing House, Basım sayısı:1, Sayfa sayısı:92, ISBN:978-605-7510-53-2, 2018.
• 6 . Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V., How to backdoor federated learning. arXiv preprint arXiv:1807.00459.2018.
• 7 . Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D., Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492.2016.
• 8 . Hard, A., Rao, K., Mathews, R., Ramaswamy, S., Beaufays, F., Augenstein, S., & Ramage, D., Federated learning for mobile keyboard prediction. arXiv preprint arXiv:1811.03604.2018.
• 9 . Wang, X., Han, Y., Wang, C., Zhao, Q., Chen, X., & Chen, M., In-edge ai: Intelligentizing mobile edge computing, caching and communication by federated learning. IEEE Network, 33(5), 156-165. 2019.
• 10 . Yang, Q., Liu, Y., Chen, T., & Tong, Y., Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2), 12, 2019.
• 11 . Nock, R., Hardy, S., Henecka, W., Ivey-Law, H., Patrini, G., Smith, G., & Thorne, B., Entity Resolution and Federated Learning get a Federated Resolution. arXiv preprint arXiv:1803.04035.2018.
• 12 . Liu, B., Wang, L., Liu, M., & Xu, C., Lifelong federated reinforcement learning: a learning architecture for navigation in cloud robotic systems. arXiv preprint arXiv:1901.06455.2019.
• 13 . Pettai, M., & Laud, P., Combining differential privacy and secure multiparty computation. In Proceedings of the 31st Annual Computer Security Applications Conference, 421-430, 2015. ACM.
• 14 . Bayatbabolghani, F., & Blanton, M., Secure Multi-Party Computation. In Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, 2157-2159, ACM.2018.
• 15 . Choudhury, O., Gkoulalas-Divanis, A., Salonidis, T., Sylla, I., Park, Y., Hsu, G., & Das, A., Differential Privacy-enabled Federated Learning for Sensitive Health Data. arXiv preprint arXiv:1910.02578. 2019.
• 16 . Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L., Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (pp. 308-318). ACM.2016.
• 17 . Yang, Y., Zhang, Z., Miklau, G., Winslett, M., & Xiao, X., Differential privacy in data publication and analysis. In Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data, 601-606. ACM.2012.
• 18 . Aslett, L. J., Esperança, P. M., & Holmes, C. C., A review of homomorphic encryption and software tools for encrypted statistical machine learning. arXiv preprint arXiv:1508.06574, 2015.
• 19 . Brakerski, Z., Fully homomorphic encryption without modulus switching from classical GapSVP. In Advances in cryptology–crypto 2012, 868–886. Springer, Berlin, Heidelberg, 2012.
• 20 . Fan, J., & Vercauteren, F., Somewhat Practical Fully Homomorphic Encryption. IACR Cryptology ePrint Archive, 2012, 144, 2012.
• 21 . Cheon, J. H., Kim, A., Kim, M., & Song, Y., Homomorphic encryption for arithmetic of approximate numbers. In International Conference on the Theory and Application of Cryptology and Information Security, 409–437. 2017. Springer, Cham.
• 22 . Yang, T., Andrew, G., Eichner, H., Sun, H., Li, W., Kong, N., & Beaufays, F., Applied federated learning: Improving google keyboard query suggestions. arXiv preprint arXiv:1812.02903. 2018.
• 23 . Galtier, M. N., & Marini, C., Substra: a framework for privacy-preserving, traceable and collaborative Machine Learning. arXiv preprint arXiv:1910.11567. 2019.
• 24 . Johnson, K., Erişim adresi: https://venturebeat.com/2019/10/13/nvidia-uses-federated-learning-to-create-medical-imaging-ai/ Erişim Tarihi: 10.12.2019
• 25 . Federated Learning for FirefoxErişim adresi: https://florian.github.io/federated-learning-firefox/ Erişim Tarihi: 10.12.2019