-
公开(公告)号:US20240062043A1
公开(公告)日:2024-02-22
申请号:US18364746
申请日:2023-08-03
Applicant: NEC Laboratories America, Inc.
Inventor: Liang Tong , Zhengzhang Chen , Wei Cheng , Haifeng Chen , Zhuohang Li
IPC: G06N3/0455 , G06N3/08
CPC classification number: G06N3/0455 , G06N3/08
Abstract: A computer-implemented method for employing a graph-based adaptive domain generation framework is provided. The method includes, in a training phase, performing domain prototypical network training on source domains, constructing an autoencoding domain relation graph by applying a graph autoencoder to produce domain node embeddings, and performing, via a domain-adaptive classifier, domain-adaptive classifier training to make an informed decision. The method further includes, in a testing phase, given testing samples from a new source domain, computing a prototype by using a pretrained domain prototypical network, inferring node embedding, and making a prediction by the domain-adaptive classifier based on the domain node embeddings.