Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis
Open accessAbstract
Tensor factorization has been demonstrated as an efficient approach for computational phenotyping, where massive electronic health records (EHRs) are converted to concise and meaningful clinical concepts. While distributing the tensor factorization tasks to local sites can avoid direct data sharing, it still requires the exchange of intermediary results which could reveal sensitive patient information. Therefore, the challenge is how to jointly decompose the tensor under rigorous and principled privacy constraints, while still support the model's interpretability. We propose DPFact, a privacy-preserving collaborative tensor factorization method for computational phenotyping using EHR. It embeds advanced privacy-preserving mechanisms with collaborative learning. Hospitals can keep their EHR database private but also collaboratively learn meaningful clinical concepts by sharing differentially private intermediary results. Moreover, DPFact solves the heterogeneous patient population using a structured sparsity term. In our framework, each hospital decomposes its local tensors and sends the updated intermediary results with output perturbation every several iterations to a semi-trusted server which generates the phenotypes. The evaluation on both real-world and synthetic datasets demonstrated that under strict privacy constraints, our method is more accurate and communication-efficient than state-of-the-art baseline methods.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The field of secure multi-party computation has moved from being of purely theoretical interest to a deployed technology in industry.
“Thanks to both theoretical and engineering breakthroughs, the field has moved from being of a purely theoretical interest to a deployed technology in industry [78, 77, 295, 27, 191, 242, 243].”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [77]
The Conclusion and §5.3 Implementation Details describe a differentially private tensor-factorization method tested on datasets using AWS instances. Searches for secure multi-party computation and industrial deployment found no passage in our copy addressing the claimed shift from theory to deployed industry technology. (LLM, conf=0.76)
Experimental — accuracy not yet measuredDistributed local-updating primal methods have been applied with success for both convex and non-convex objectives.
“For both convex and non-convex objectives, distributed local-updating primal methods have also been applied with success [137].”
From Challenges, Applications and Design Aspects of Federated Learning: A Survey (2021) · cites this paper as [137]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · see citing works
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961 · see citing works
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377 · see citing works
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
Bun, M., & Steinke, T. (2016) · Theory of Cryptography Conference · doi:10.1007/978-3-662-53641-4_24 · Cited by 1,045 · see citing works
Boosting and Differential Privacy
Dwork, C., Rothblum, G. N., & Vadhan, S. (2010) · 2010 IEEE 51st Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2010.12 · Cited by 784 · see citing works
Greenhalgh, T., Hinder, S., Stramer, K., Bratan, T., & Russell, J. (2010) · BMJ · doi:10.1136/bmj.c5814 · Cited by 343 · see citing works
On Tensors, Sparsity, and Nonnegative Factorizations
Chi, E. C., & Kolda, T. G. (2012) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/110859063 · Cited by 274 · see citing works
Kang, U., Papalexakis, E. E., Harpale, A., & Faloutsos, C. (2012) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2339530.2339583 · Cited by 238 · see citing works
Ho, J. C., Ghosh, J., & Sun, J. (2014) · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2623330.2623658 · Cited by 214 · see citing works
Self-citationBolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics
Wu, X., Li, F., Kumar, A., Chaudhuri, K., Jha, S., & Naughton, J. F. (2017) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3035918.3064047 · Cited by 182 · see citing works
Wang, Y., Chen, R. F., Ghosh, J., Denny, J. C., Kho, A. N., Chen, Y., Malin, B., & Sun, J. (2015) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2783258.2783395 · Cited by 157 · see citing works
Federated Tensor Factorization for Computational Phenotyping
Kim, Y., Sun, J., Yu, H., & Jiang, X. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098118 · Cited by 128 · see citing works
Self-citationApplying Differential Privacy to Matrix Factorization
Berlioz, A., Friedman, A., Kâafar, M. A., Boreli, R., & Berkovsky, S. (2015) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/2792838.2800173 · Cited by 126 · see citing works
F lexi F a CT: Scalable Flexible Factorization of Coupled Tensors on Hadoop
Beutel, A., Talukdar, P. P., Kumar, A., et al. (2014) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611973440.13 · Cited by 107 · see citing works
Fast Differentially Private Matrix Factorization
Liu, Z., Wang, Y.-X., & Smola, A. J. (2015) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/2792838.2800191 · Cited by 92 · see citing works
Hospital Phenotypes in the Management of Patients Admitted for Acute Myocardial Infarction
Xu, X. J., Li, S., Lin, H., Normand, S. T., Lagu, T. C., Desai, N. R., Duan, M., Kroch, E. A., & Krumholz, H. M. (2016) · Medical Care · doi:10.1097/mlr.0000000000000571 · Cited by 4 · see citing works
Flagged first, then by citations
Research works printed but not linked: 23
- Alex Beutel, Partha Pratim Talukdar, Abhimanu Kumar, Christos Faloutsos, Evan- gelos E Papalexakis, and Eric P Xing. 2014. Flexifact: Scalable flexible factorization of coupled tensors on hadoop. In Proceedings of the 2014 SDM. 109-117.
- Joon Hee Choi and S Vishwanathan. 2014. DFacTo: Distributed factorization of tensors. In NIPS. 1296-1304.
- Patrick L Combettes and Jean-Christophe Pesquet. 2011. Proximal splitting methods in signal processing. In Fixed-point algorithms for inverse problems in science and engineering. Springer, 185-212.
- Cynthia Dwork, Aaron Roth, et al. 2014. The algorithmic foundations of differ- ential privacy. Foundations and Trends® in Theoretical Computer Science 9, 3-4 (2014), 211-407.
- Cynthia Dwork and Guy N Rothblum. 2016. Concentrated differential privacy. arXiv preprint arXiv:1603.01887 (2016). · arXiv
- Cynthia Dwork, Guy N Rothblum, and Salil Vadhan. 2010. Boosting and differ- ential privacy. In 2010 IEEE 51st Annual Symposium on Foundations of Computer Science. IEEE, 51-60.
- Yuhong Guo and Wei Xue. 2013. Probabilistic Multi-Label Classification with Sparse Feature Learning.. In IJCAI. 1373-1379.
- Joyce C Ho, Joydeep Ghosh, and Jimeng Sun. 2014. Marble: high-throughput phenotyping from electronic health records via sparse nonnegative tensor fac- torization. In Proceedings of the 20th ACM SIGKDD. ACM, 115-124.
- Jingyu Hua, Chang Xia, and Sheng Zhong. 2015. Differentially Private Matrix Factorization.. In IJCAI. 1763-1770.
- Alistair EW Johnson, Tom J Pollard, Lu Shen, H Lehman Li-wei, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific data 3 (2016), 160035.
- U Kang, Evangelos Papalexakis, Abhay Harpale, and Christos Faloutsos. 2012. Gigatensor: scaling tensor analysis up by 100 times-algorithms and discoveries. In Proceedings of the 18th ACM SIGKDD. ACM, 316-324.
- Yejin Kim, Robert El-Kareh, Jimeng Sun, Hwanjo Yu, and Xiaoqian Jiang. 2017. Discriminative and distinct phenotyping by constrained tensor factorization. Scientific reports 7, 1 (2017), 1114.
- Jun Liu, Shuiwang Ji, and Jieping Ye. 2009. Multi-task feature learning via efficient ℓ 2, 1 -norm minimization. In UAI. 339-348.
- Jing Ma, Qiuchen Zhang, Jian Lou, Joyce C Ho, Li Xiong, and Xiaoqian Jiang. 2019. Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis. arXiv preprint arXiv:1908.09888 (2019). · arXiv
- Feiping Nie, Heng Huang, Xiao Cai, and Chris H Ding. 2010. Efficient and robust feature selection via joint ℓ 2, 1 -norms minimization. In NeurIPS. 1813-1821.
- Rachel L Richesson, Jimeng Sun, Jyotishman Pathak, Abel N Kho, and Joshua C Denny. 2016. Clinical phenotyping in selected national networks: demonstrating the need for high-throughput, portable, and computational methods. Artificial intelligence in medicine 71 (2016), 57-61.
- Yining Wang and Anima Anandkumar. 2016. Online and differentially-private tensor decomposition. In NeurIPS. 3531-3539.
- Yichen Wang, Robert Chen, Joydeep Ghosh, Joshua C Denny, Abel Kho, You Chen, Bradley A Malin, and Jimeng Sun. 2015. Rubik: Knowledge guided tensor factorization and completion for health data analytics. In Proceedings of the 21th ACM SIGKDD. ACM, 1265-1274.
- Wei-Qi Wei and Joshua C Denny. 2015. Extracting research-quality phenotypes from electronic health records to support precision medicine. Genome medicine 7, 1 (2015), 41.
- Yi Yang, Heng Tao Shen, Zhigang Ma, Zi Huang, and Xiaofang Zhou. 2011. ℓ 2, 1 - norm regularized discriminative feature selection for unsupervised learning. In IJCAI, Vol. 22. 1589.
- Doaa Youssef, Hadeel Abd-Elrahman, Mohamed M Shehab, Mohamed Abd- Elrheem, et al. 2015. Incidence of acute kidney injury in the neonatal intensive care unit. Saudi journal of kidney diseases and transplantation 26, 1 (2015), 67.
- Lei Yu, Ling Liu, Calton Pu, Mehmet Emre Gursoy, and Stacey Truex. 2019. Differentially Private Model Publishing for Deep Learning. arXiv preprint arXiv:1904.02200 (2019). · arXiv
- Sixin Zhang, Anna E Choromanska, and Yann LeCun. 2015. Deep learning with elastic averaging SGD. In NeurIPS. 685-693.
Cited by
Sorted by citations
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772 · see citing works
A survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480 · see citing works
Lo, S. K., Lu, Q., Wang, C., Paik, H.-Y., & Zhu, L. (2022) · ACM Computing Surveys · doi:10.1145/3450288 · Cited by 202 · see citing works
Challenges, Applications and Design Aspects of Federated Learning: A Survey
Rahman, K. M. J., Ahmed, F., Akhter, N., Hasan, M., Amin, R., Aziz, K. E., Islam, A. K. M. M., Mukta, M. S. H., & Islam, A. K. M. N. (2021) · IEEE Access · doi:10.1109/access.2021.3111118 · Cited by 147 · see citing works
- Authors
- Ma, J., Zhang, Q., Lou, J., Ho, J. C., Xiong, L., & Jiang, X.
- Affiliations
- Emory University (US)
- The University of Texas Health Science Center at Houston (US)
- ORCID
- Jiang, Xiaoqian
- Venue
- Proceedings of the 28th ACM International Conference on Information and Knowledge Management
- Publisher
- ACM
- Published
- 2019-11-03
- Volume
- 2019
- Pages
- 1291-1300
- ISSN
- 2155-0751 (ISSN-L)
- PMC
- PMC6940039
- OpenAlex
- W2970406589
- Cited by
- 51
- References
- 16
- Citations by year
- 2026: 4 · 2025: 6 · 2024: 10 · 2023: 7 · 2022: 6 · 2021: 11 · 2020: 7
- FWCI
- 2.30
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM International Conference on Information and Knowledge Management (CIKM) (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Institutes of Health (R01GM118609)
- National Science Foundation (1838200)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Mathematics › Computational Mathematics › Tensor decomposition and applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- computational phenotyping, electronic health records, differential privacy, cooperative learning, federated learning, structured sparsity, heterogeneous patient populations, communication efficiency, clinical concept extraction
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
