Learning Privately over Distributed Features: An ADMM Sharing Approach

Distributed machine learning has been widely studied in order to handle exploding amount of data. In this paper, we study an important yet less visited distributed learning problem where features are inherently distributed or vertically partitioned among multiple parties, and sharing of raw data or model parameters among parties is prohibited due to privacy concerns. We propose an ADMM sharing framework to approach risk minimization over distributed features, where each party only needs to share a single value for each sample in the training process, thus minimizing the data leakage risk. We establish convergence and iteration complexity results for the proposed parallel ADMM algorithm under non-convex loss. We further introduce a novel differentially private ADMM sharing algorithm and bound the privacy guarantee with carefully designed noise perturbation. The experiments based on a prototype system shows that the proposed ADMM algorithms converge efficiently in a robust fashion, demonstrating advantage over gradient based methods especially for data set with high dimensional feature spaces.

[1]  Hideki Hashimoto,et al.  Privacy-Preserving Multiple Linear Regression of Vertically Partitioned Real Medical Datasets , 2017, 2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA).

[2]  Ehsan Hesamifard,et al.  Preserving Multi-party Machine Learning with Homomorphic Encryption , 2016 .

[3]  Stefan Werner,et al.  Distributed Ridge Regression with Feature Partitioning , 2018, 2018 52nd Asilomar Conference on Signals, Systems, and Computers.

[4]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[5]  Payman Mohassel,et al.  SecureML: A System for Scalable Privacy-Preserving Machine Learning , 2017, 2017 IEEE Symposium on Security and Privacy (SP).

[6]  Ian Goodfellow,et al.  Deep Learning with Differential Privacy , 2016, CCS.

[7]  Katharina Morik,et al.  Sustainable Industrial Processes by Embedded Real-Time Quality Prediction , 2016, Computational Sustainability.

[8]  Steve R. Gunn,et al.  Result Analysis of the NIPS 2003 Feature Selection Challenge , 2004, NIPS.

[9]  Anand D. Sarwate,et al.  Signal Processing and Machine Learning with Differential Privacy: Algorithms and Challenges for Continuous Data , 2013, IEEE Signal Processing Magazine.

[10]  Kamalika Chaudhuri,et al.  Privacy-preserving logistic regression , 2008, NIPS.

[11]  Qing Ling,et al.  On the Linear Convergence of the ADMM in Decentralized Consensus Optimization , 2013, IEEE Transactions on Signal Processing.

[12]  Quanyan Zhu,et al.  Dynamic Differential Privacy for ADMM-Based Distributed Classification Learning , 2017, IEEE Transactions on Information Forensics and Security.

[13]  Cynthia Dwork,et al.  Differential Privacy: A Survey of Results , 2008, TAMC.

[14]  Yaoliang Yu,et al.  On Convergence of Model Parallel Proximal Gradient Algorithm for Stale Synchronous Parallel System , 2016, AISTATS.

[15]  Alexander J. Smola,et al.  Scaling Distributed Machine Learning with the Parameter Server , 2014, OSDI.

[16]  Quanyan Zhu,et al.  A Dual Perturbation Approach for Differential Private ADMM-Based Distributed Empirical Risk Minimization , 2016, AISec@CCS.

[17]  Chris Clifton,et al.  Privacy-preserving k-means clustering over vertically partitioned data , 2003, KDD '03.

[18]  Zhifeng Xiao,et al.  Security and Privacy in Cloud Computing , 2013, IEEE Communications Surveys & Tutorials.

[19]  Aaron Roth,et al.  The Algorithmic Foundations of Differential Privacy , 2014, Found. Trends Theor. Comput. Sci..

[20]  Arun Rajkumar,et al.  A Differentially Private Stochastic Gradient Descent Algorithm for Multiparty Classification , 2012, AISTATS.

[21]  Christina Heinze-Deml,et al.  Preserving privacy between features in distributed estimation , 2017, ArXiv.

[22]  S. K. Dubey,et al.  Security and Privacy in Cloud Computing: A Survey , 2013 .

[23]  Vitaly Shmatikov,et al.  Privacy-preserving deep learning , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[24]  Zhi-Quan Luo,et al.  Convergence analysis of alternating direction method of multipliers for a family of nonconvex problems , 2014, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[25]  Di Niu,et al.  FDML: A Collaborative Machine Learning Framework for Distributed Features , 2019, KDD.

[26]  Onur Mutlu,et al.  Gaia: Geo-Distributed Machine Learning Approaching LAN Speeds , 2017, NSDI.

[27]  Alexander J. Smola,et al.  Communication Efficient Distributed Machine Learning with the Parameter Server , 2014, NIPS.

[28]  Mingyan Liu,et al.  Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms , 2018, ICML.

[29]  Xiaoqian Jiang,et al.  Privacy Preserving Federated Big Data Analysis , 2018 .

[30]  Wotao Yin,et al.  Global Convergence of ADMM in Nonconvex Nonsmooth Optimization , 2015, Journal of Scientific Computing.

[31]  Ali H. Sayed,et al.  Supervised Learning Under Distributed Features , 2018, IEEE Transactions on Signal Processing.

[32]  Bhiksha Raj,et al.  Multiparty Differential Privacy via Aggregation of Locally Trained Classifiers , 2010, NIPS.

[33]  Rui Hu,et al.  DP-ADMM: ADMM-Based Distributed Learning With Differential Privacy , 2018, IEEE Transactions on Information Forensics and Security.

[34]  Seunghak Lee,et al.  More Effective Distributed ML via a Stale Synchronous Parallel Parameter Server , 2013, NIPS.

[35]  Cynthia Dwork,et al.  Privacy-Preserving Datamining on Vertically Partitioned Databases , 2004, CRYPTO.

[36]  Alexandre V. Evfimievski,et al.  Privacy preserving mining of association rules , 2002, Inf. Syst..

[37]  Gu Si-yang,et al.  Privacy preserving association rule mining in vertically partitioned data , 2006 .

[38]  Nina Mishra,et al.  Privacy via the Johnson-Lindenstrauss Transform , 2012, J. Priv. Confidentiality.

[39]  Li Wan,et al.  Privacy-preservation for gradient descent methods , 2007, KDD '07.

[40]  Anand D. Sarwate,et al.  Differentially Private Empirical Risk Minimization , 2009, J. Mach. Learn. Res..

[41]  Yongqiang Wang,et al.  ADMM Based Privacy-Preserving Decentralized Optimization , 2017, IEEE Transactions on Information Forensics and Security.

[42]  Frederik Vercauteren,et al.  Privacy-preserving logistic regression training , 2018, BMC Medical Genomics.

[43]  Michael Naehrig,et al.  CryptoNets: applying neural networks to encrypted data with high throughput and accuracy , 2016, ICML 2016.

[44]  Mikhail Belkin,et al.  Learning privately from multiparty data , 2016, ICML.