Microsoft Technology Licensing, LLC

Tianhao Lu

Yunpeng Xu

Dan Shacham

Chencheng Wu

Hong H Tam

Jiashuo Wang

Junzhe Miao

Xiaoqiang Luo

Tao Xiong

Techniques for securely storing and processing data for training data generation are provided. In one technique, multiple encrypted records are retrieved from a first persistent storage. For each encrypted record, that record is decrypted in memory to generate a decrypted record that comprises multiple attribute values. Then, based on the attribute values and a definition of multiple features of a machine-learned model, multiple feature values are generated and stored, along with a label, in a training instance, which is then stored in a second persistent storage. One or more machine learning techniques are used to train the machine-learned model based on training data that includes the training instances that are stored in the second persistent storage.

Secure storage and processing of data for generating training data

The disclosed embodiments provide a system that identifies duplicate entities. During operation, the system selects training data for a first machine learning model based on confidence scores representing likelihoods that pairs of entities in an online system are duplicates. Next, the system updates parameters of the first machine learning model based on features and labels in the training data. The system then identifies a first subset of additional pairs of the entities as duplicate entities based on scores generated by the first machine learning model from values of the features for the additional pairs and a first threshold associated with the scores. The system also determines a canonical entity in each of the duplicate entities based on additional features. Finally, the system updates content outputted in a user interface of the online system based on the identified first subset of the additional pairs.

Identifying duplicate entities

Growing community of inventors

New York, NY, United States of America

Tianhao Lu