Forgetting verification method based on semantic data loss in federated learning

Abstract

The invention discloses a forgetting verification method based on semantic data loss in federated learning, and the method employs specific performances on some data which are high in loss, are commonly wrong, and are provided with a certain semantic feature to mark forgetting users and verify forgetting conditions. The method comprises the following steps: screening out data with high loss and general classification errors in a local data set, and re-marking the data as a certain fixed category according to similarity and confidence distribution of semantic features of the data to obtain a marked data set; and uploading the marked model after the local model is finely adjusted on the data set and the original data set to a central server for aggregation. The forgetting user verifies the forgetting condition according to the loss of the global model on the marked data set by checking the global model of the next plurality of cycles. The method has the advantages of being lightweight, high in continuity, good in verification effect, small in time and space overhead and the like, can effectively identify whether forgetting occurs or not, and can be widely applied and deployed in various scenes needing forgetting verification.

Description

technical field [0001] The invention relates to the field of federated learning data forgetting verification, in particular to a method for forgetting verification based on semantic data loss in federated learning. Background technique [0002] Federated learning has emerged as a privacy-preserving distributed collaborative learning framework where all participants can jointly train a powerful model without sharing their private data. A fundamental requirement of federated learning is to allow participants to join or leave freely without concern, i.e. private data about leaving users should be actively forgotten by the central server. Users who leave have the right to have their data forgotten, a right already enshrined in some data laws, such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA), among others. There are already some methods of active forgetting, such as retraining, etc. However, the specific forgetting operation i...

AI Technical Summary

Problems solved by technology

However, the specific forgetting operation is not the main concern of the user. The user is more concerned about whether the forgetting can be verified and how to verify it, that is, whether my personal data has been successfully forgotten and how effective the forgetting is.

However, the forgetting verification in federated learning cannot be judged by the performance of simple forgotten data, because federated learning is a distributed collaborative learning framework, and individual withdrawal has little impact on large-scale federated learning, and the contribution of others makes federated learning The global model still maintains good performance on the personal data of exit users

Images