APPARATUS AND METHOD FOR DISTRIBUTED TRAINING MODEL, AND COMPUTER PROGRAM PRODUCT

• Main Authors: MA, Lin, YU, Dianhai, WU, Zhihua, TANG, Wei, CHENG, Mo, MA, Yanjun, WU, Xinxuan, WANG, Haifeng, YAO, Xuefeng, WU, Tian
• Format: Patent
• Language: English; French; German
• Published: 22.06.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The present disclosure discloses an apparatus and method for distributed training a model, an electronic device, a computer readable storage medium, and a computer program product, and relates to the field of deep learning technology. An embodiment of the apparatus includes: a distributed reader, a distributed trainer and a distributed parameter server that are mutually independent. A reader in the distributed reader is configured to acquire a training sample, and load the acquired training sample to a corresponding trainer in the distributed trainer; the trainer in the distributed trainer is configured to perform model training based on the loaded training sample to obtain gradient information; and a parameter server in the distributed parameter server is configured to update a parameter of an initial model based on the gradient information of the distributed trainer to obtain a trained target model. This embodiment provides an apparatus training a distributed model. In the model training process, the modules are independent of each other and run in cooperation, improving a model training speed.