Differentially Private Generative Adversarial Network — mentioned by snowpid

Wed, 11 Jan 2023 13:39:31 GMT

If the data is sparse, some researches used AI generated content to train another network. E.G. https://arxiv.org/pdf/1802.06739.pdf In some cases like here it also has privacy issues.

Paper and discussion history. A mention is not an endorsement.

Differentially Private Generative Adversarial Network — mentioned by jaster

Mon, 26 Feb 2018 09:16:19 GMT

Fun coincidence (or maybe not?), I just stumbled upon the following paper on arvix titled "Differentially Private Generative Adversarial Network" https://arxiv.org/pdf/1802.06739v1.pdf Its Related Work section also references some works on "differentially private learning in neural network". While the paper does not discuss directly OP remark about how differential privacy could help generality in machine learning, it shows that at least some connections exist between the domains.

Paper and discussion history. A mention is not an endorsement.

Differentially Private Generative Adversarial Network · HackerPapers discussions

Differentially Private Generative Adversarial Network — mentioned by snowpid

Differentially Private Generative Adversarial Network — mentioned by jaster