Causally Constrained Data Synthesis For Private Data Release

Varun Chandrasekaran, Darren Edge, Somesh Jha, Lukas Wutschitz, Amit Sharma, Cheng Zhang, Shruti Tople

Abstract: Data privacy is critical in many decision-making contexts, such as healthcare and finance. A common mechanism is to create differentially private synthetic data using generative models. Such data generation reflects certain statistical properties of the original data, but often has an unacceptable privacy vs. utility trade-off. Since natural data inherently exhibits causal structure, we propose incorporating \emph{causal information} into the training process to favorably navigate the aforementioned trade-off. Under certain assumptions for linear gaussian models and a broader class of models, we theoretically prove that causally informed generative models provide better differential privacy guarantees than their non-causal counterparts. We evaluate our proposal using variational autoencoders, and demonstrate that the trade-off is mitigated through better utility for comparable privacy.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2105.13144/code)