PROTECTED TRAINING OF PRIVATE ADAPTER MODELS FOR A HOSTED FOUNDATION MODEL
개요
발명자
Marian Radu; Paul Sumedrea
IPC 분류
CPC 분류
Methods and systems are provided for training copies of a private adapter network at respective client computing devices; and aggregating of trained weight sets in a common parameter space as a weight set of a hosted foundation model at a cloud computing system. A private adapter model can be a subdivision of a hosted foundation model, segmented from some number of layers of a hosted foundation model or can be distinct from the hosted foundation model, given that the private adapter model configures a computing host to update a weight set in a common parameter space as a weight set of the hosted foundation model. By performing a protected update to a weight set, true values of the coefficients of the weight set derived from inputting features of a labeled dataset at a first layer of the private adapter model are obfuscated.
원문 (중국어)
Methods and systems are provided for training copies of a private adapter network at respective client computing devices; and aggregating of trained weight sets in a common parameter space as a weight set of a hosted foundation model at a cloud computing system. A private adapter model can be a subdivision of a hosted foundation model, segmented from some number of layers of a hosted foundation model or can be distinct from the hosted foundation model, given that the private adapter model configures a computing host to update a weight set in a common parameter space as a weight set of the hosted foundation model. By performing a protected update to a weight set, true values of the coefficients of the weight set derived from inputting features of a labeled dataset at a first layer of the private adapter model are obfuscated.
로그인하고 전문 읽기
청구항 1을 표시했습니다. 무료 가입하면 전체 16개 청구항, 명세서 전문, 전체 도면, 번역, 법적 상태를 볼 수 있습니다.
- 전체 청구항
- 도면 설명
- 발명의 실시 형태