Salesforce, inc. (20250077878). TRANSFORMER-BASED ADVERSARIAL ACTIVE LEARNING SYSTEM

From WikiPatents
Jump to navigation Jump to search

TRANSFORMER-BASED ADVERSARIAL ACTIVE LEARNING SYSTEM

Organization Name

salesforce, inc.

Inventor(s)

Xiaolin Pang of San Francisco CA (US)

Kexin Xie of San Francisco CA (US)

Max Fleming of San Francisco CA (US)

Chen Xu of San Francisco CA (US)

Yuxi Zhang of San Francisco CA (US)

TRANSFORMER-BASED ADVERSARIAL ACTIVE LEARNING SYSTEM

This abstract first appeared for US patent application 20250077878 titled 'TRANSFORMER-BASED ADVERSARIAL ACTIVE LEARNING SYSTEM

Original Abstract Submitted

system and method for transformer-based adversarial active learning system. a machine learning system includes a generator, a transformer encoder, a classifier, and a discriminator all working in combination to generate and select unlabeled data points for labeling. the system utilizes a generative adversarial network paired with an active learning framework to optimize text embedding and feature encoding according to distribution of training data.