Distributed Differentially Private Algorithms for Matrix and Tensor Factorization
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
In many signal processing and machine learning applications, datasets containing private information are held at different locations, requiring the development of distributed privacy-preserving algorithms. Tensor and matrix factorizations are key components of many processing pipelines. In the distributed setting, differentially private algorithms suffer because they introduce noise to guarantee privacy. This paper designs new and improved distributed and differentially private algorithms for two popular matrix and tensor factorization methods: principal component analysis (PCA) and orthogonal tensor decomposition (OTD). The new algorithms employ a correlated noise design scheme to alleviate the effects of noise and can achieve the same noise level as the centralized scenario. Experiments on synthetic and real data illustrate the regimes in which the correlated noise allows performance matching with the centralized setting, outperforming previous methods and demonstrating that meaningful utility is possible while guaranteeing differential privacy.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Distributed Subgradient Methods for Multi-Agent Optimization
Nedic, A., & Ozdaglar, A. (2009) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.2009515 · Cited by 3,719
Distributed asynchronous deterministic and stochastic gradient optimization algorithms
Tsitsiklis, J., Bertsekas, D., & Athans, M. (1986) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1986.1104412 · Cited by 1,967
RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
Erlingsson, Ú., Pihur, V., & Korolova, A. (2014) · Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2660267.2660348 · Cited by 1,838
Our Data, Ourselves: Privacy Via Distributed Noise Generation
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., & Naor, M. (2006) · Lecture Notes in Computer Science · doi:10.1007/11761679_29 · Cited by 1,835
Performance evaluation of some clustering algorithms and validity indices
Maulik, U., & Bandyopadhyay, S. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1114856 · Cited by 1,396
The Expression of a Tensor or a Polyadic as a Sum of Products
Hitchcock, F. L. (1927) · Journal of Mathematics and Physics · doi:10.1002/sapm192761164 · Cited by 1,345
Tensor decompositions for learning latent variable models
(2012) · arXiv (Cornell University) · doi:10.5555/2627435.2697055 · Cited by 779 · cited 23×
“[3], namely the single topic model (STM) and the mixture of Gaussian (MOG), are presented in Appendix B.”
BackgroundMethodInfluentialComputation Over Multiple-Access Channels
Nazer, B., & Gastpar, M. (2007) · IEEE Transactions on Information Theory · doi:10.1109/tit.2007.904785 · Cited by 753
Prochlo: Strong Privacy for Analytics in the Crowd
Bittau, A., Erlingsson, Ú., Maniatis, P., Mironov, I., Raghunathan, A., Lie, D., Rudominer, M., Kode, U., Tinnes, J., & Seefeld, B. (2017) · Proceedings of the 26th Symposium on Operating Systems Principles · doi:10.1145/3132747.3132769 · Cited by 378
Cited by
When Machine Learning Meets Privacy: A Survey and Outlook
Liu, B., Ding, M., Shaham, S., Rahayu, W., Farokhi, F., & Lin, Z. (2022) · ACM Computing Surveys · doi:10.1145/3436755 · Cited by 455
FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models
Liu, G., Ma, X., Yang, Y., Wang, C., & Liu, J. (2021) · 2021 IEEE/ACM 29th International Symposium on Quality of Service (IWQOS) · doi:10.1109/iwqos52092.2021.9521274 · Cited by 248
“There have been a series of differentially private versions of ML algorithms, including linear models [26], principal component analysis [27], matrix factorization [28], and DNN [29], the parameters of which are learned via adding noise in the training phase.”
MethodWhen Machine Learning Meets Privacy in 6G: A Survey
Sun, Y., Liu, J., Wang, J., Cao, Y., & Kato, N. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3011561 · Cited by 211
“Imtiaz and Sarwate propose new algorithms combining distributed training with differentially-private principal to realize Singular Value Decomposition (SVD), Principal Component Analysis (PCA), and orthogonal tensor decomposition [58].”
BackgroundMethodA Survey on Differentially Private Machine Learning [Review Article]
Gong, M., Xie, Y., Pan, K., Feng, K., & Qin, A. K. (2020) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2020.2976185 · Cited by 115
Metadata
- Authors
- Imtiaz, H., & Sarwate, A. D.
- Venue
- IEEE Journal of Selected Topics in Signal Processing
- Published
- 2018-12
- Volume
- 12
- Issue
- 6
- Pages
- 1449-1464
- ISSN
- 1932-4553 (ISSN-L)
- 1941-0484
- OpenAlex
- W2798559676
- Cited by
- 35
- References
- 10
- FWCI
- 2.83
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Distributed Differentially Private Algorithms for Matrix and Tensor Factorization. https://app.cochat.ai/papers/10.1109/jstsp.2018.2877842
- The paper
- Imtiaz, H., & Sarwate, A. D. (2018). Distributed Differentially Private Algorithms for Matrix and Tensor Factorization. IEEE Journal of Selected Topics in Signal Processing. https://doi.org/10.1109/jstsp.2018.2877842
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.