Machine Unlearning for Uplink Interference Cancellation

TL;DR

This paper introduces machine unlearning (MUL) as a novel method for interference cancellation in AI-enabled wireless systems, improving classification accuracy and eliminating the need for retraining or dataset cleansing.

Contribution

It presents a new MUL algorithm that effectively cleanses interference noise from latent spaces without retraining, enhancing AI model robustness in wireless communications.

Findings

30% improvement in classification accuracy with MUL

Eliminates need for instantaneous channel state information

Reduces retraining and dataset cleansing requirements

Abstract

Machine unlearning (MUL) is introduced as a means to achieve interference cancellation within artificial intelligence (AI)-enabled wireless systems. It is observed that interference cancellation with MUL demonstrates $30\%$ improvement in a classification task accuracy in the presence of a corrupted AI model. Accordingly, the necessity for instantaneous channel state information for existing interference source is eliminated and a corrupted latent space with interference noise is cleansed with MUL algorithm, achieving this without the necessity for either retraining or dataset cleansing. A Membership Inference Attack (MIA) served as a benchmark for assessing the efficacy of MUL in mitigating interference within a neural network model. The advantage of the MUL algorithm was determined by evaluating both the probability of interference and the quantity of samples requiring retraining. In a simple signal-to-noise ratio classification task, the comprehensive improvement across various test cases in terms of accuracy demonstrates that MUL exhibits extensive capabilities and limitations, particularly in native AI applications.