公开(公告)号：US11699080B2

公开(公告)日：2023-07-11

申请号：US16131150

申请日：2018-09-14

Applicant: Cisco Technology, Inc.

Inventor： Xiaoqing Zhu ,  Yaqi Wang ,  Dan Tan ,  Rob Liston ,  Mehdi Nikkhah

IPC: G06N20/00 ,  G06N20/10 ,  G06N3/088 ,  G06N3/045 ,  G06N5/01 ,  G06F18/214 ,  H04Q9/00 ,  G06F9/48 ,  G06F18/25

CPC classification number: G06F18/2155 ,  G06F9/48 ,  G06F18/253 ,  G06N3/045 ,  G06N3/088 ,  G06N5/01 ,  G06N20/00 ,  G06N20/10 ,  H04Q9/00

Abstract: In one embodiment, a service receives machine learning-based generative models from a plurality of distributed sites. Each generative model is trained locally at a site using unlabeled data observed at that site to generate synthetic unlabeled data that mimics the unlabeled data used to train the generative model. The service receives, from each of the distributed sites, a subset of labeled data observed at that site. The service uses the generative models to generate synthetic unlabeled data. The service trains a global machine learning-based model using the received subsets of labeled data received from the distributed sites and the synthetic unlabeled data generated by the generative models.

公开(公告)号：US20200090002A1

公开(公告)日：2020-03-19

申请号：US16131150

申请日：2018-09-14

Applicant: Cisco Technology, Inc.

Inventor： Xiaoqing Zhu ,  Yaqi Wang ,  Dan Tan ,  Rob Liston ,  Mehdi Nikkhah

IPC: G06K9/62 ,  G06F15/18 ,  G06N3/04 ,  H04Q9/00

Abstract: In one embodiment, a service receives machine learning-based generative models from a plurality of distributed sites. Each generative model is trained locally at a site using unlabeled data observed at that site to generate synthetic unlabeled data that mimics the unlabeled data used to train the generative model. The service receives, from each of the distributed sites, a subset of labeled data observed at that site. The service uses the generative models to generate synthetic unlabeled data. The service trains a global machine learning-based model using the received subsets of labeled data received from the distributed sites and the synthetic unlabeled data generated by the generative models.