ADOBE INC. (20250086495). MODEL GENERATION TECHNIQUES BASED ON AGGREGATION OF PARTIAL DATA

MODEL GENERATION TECHNIQUES BASED ON AGGREGATION OF PARTIAL DATA

Organization Name

ADOBE INC.

Inventor(s)

Saayan Mitra of San Jose CA (US)

Xiang Chen of San Jose CA (US)

Sapthotharan Krishnan Nair of Santa Clara CA (US)

Renzhi Wu of Atlanta GA (US)

Anup Rao of San Jose CA (US)

MODEL GENERATION TECHNIQUES BASED ON AGGREGATION OF PARTIAL DATA

This abstract first appeared for US patent application 20250086495 titled 'MODEL GENERATION TECHNIQUES BASED ON AGGREGATION OF PARTIAL DATA

Original Abstract Submitted

an edge node included in a decentralized edge computing network generates a federated partial-data aggregation machine learning model. the edge node learns one or more model parameters via machine learning techniques and receives one or more auxiliary model parameters from additional edge nodes in the decentralized edge computing network, such as from a neighbor node group. in some cases, a neighbor node is identified in response to determining that the neighbor node includes a model with a relatively high estimated relevance to the model of the edge node. the edge node modifies the model to include an aggregation of the learned model parameters and the received auxiliary parameters. respective weights are learned for the learned model parameters and also for the received auxiliary parameters. during training to learn the respective weights, the edge node stabilizes the learned model parameters and the received auxiliary parameters.