公开(公告)号：US20230161899A1

公开(公告)日：2023-05-25

申请号：US17535398

申请日：2021-11-24

Applicant: Lemon Inc.

Inventor： Xin Yang ,  Yuanshun Yao ,  Tianyi Liu ,  Jiankai Sun ,  Chong Wang ,  Ruihan Wu

IPC: G06F21/62

CPC classification number: G06F21/6245

Abstract: The present disclosure describes techniques of releasing data while protecting individual privacy. A dataset may be compressed by applying a first random matrix. The dataset may be owned by a party among a plurality of parties and there may be a plurality of datasets owned by the plurality of parties. A noise may be added by applying a random Gaussian matrix to the compressed dataset to obtain a processed dataset. The processed dataset ensures data privacy protection. The processed dataset may be released to other parties.

公开(公告)号：US20230143789A1

公开(公告)日：2023-05-11

申请号：US18149462

申请日：2023-01-03

Applicant: Lemon Inc.

Inventor： Shangyu Xie ,  Jiankai Sun ,  Xin Yang ,  Yuanshun Yao ,  Tianyi Liu ,  Taiqing Wang

IPC: G06N3/084 ,  G06N3/045

CPC classification number: G06N3/084 ,  G06N3/045

Abstract: Split learning is provided to train a composite neural network (CNN) model that is split into first and second submodels, including receiving a noise-laden backpropagation gradient, training the surrogate submodel by optimizing a gradient distance loss, and computing an updated dummy label using the first submodel and the trained surrogate submodel to infer label information of the second submodel. Noise can be added to a label of the second submodel or a shared backpropagation gradient to protect the label information.

公开(公告)号：US20240104125A1

公开(公告)日：2024-03-28

申请号：US18497675

申请日：2023-10-30

Applicant: Lemon Inc.

Inventor： Minh Chau PHAM ,  Boyi Liu ,  Zhengyu Chen ,  Yingxiang Yang ,  Jianbo Yuan ,  Hongxia Yang ,  Tianyi Liu

IPC: G06F16/332 ,  G06F16/33

CPC classification number: G06F16/3329 ,  G06F16/3344

Abstract: There are provided solutions for multiagent debate. In a method, a first and a second response representation are determined by a first and a second agent in a plurality of agents based on a first query representation for a query in a natural language, respectively, and the first and second response representations are convertible to a first and a second answer to the query in the natural language, respectively. A second query representation is obtained based on the first query representation, and at least one of the first and second response representations. A response representation is determined based on the second query representation by at least one of the first and second agents, and the response representation is convertible to an answer to the query in the natural language. These agents communicate in an embedding space without a conversion between a natural language format and an embedding format.