Timezone: »

Deep Regression Unlearning
Ayush Tarun · Vikram Chundawat · Murari Mandal · Mohan Kankanhalli

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #210
Event URL: https://github.com/ayushkumartarun/deep-regression-unlearning »

With the introduction of data protection and privacy regulations, it has become crucial to remove the lineage of data on demand from a machine learning (ML) model. In the last few years, there have been notable developments in machine unlearning to remove the information of certain training data efficiently and effectively from ML models. In this work, we explore unlearning for the regression problem, particularly in deep learning models. Unlearning in classification and simple linear regression has been considerably investigated. However, unlearning in deep regression models largely remains an untouched problem till now. In this work, we introduce deep regression unlearning methods that generalize well and are robust to privacy attacks. We propose the Blindspot unlearning method which uses a novel weight optimization process. A randomly initialized model, partially exposed to the retain samples and a copy of the original model are used together to selectively imprint knowledge about the data that we wish to keep and scrub off the information of the data we wish to forget. We also propose a Gaussian fine tuning method for regression unlearning. The existing unlearning metrics for classification are not directly applicable to regression unlearning. Therefore, we adapt these metrics for the regression setting. We conduct regression unlearning experiments for computer vision, natural language processing and forecasting applications. Our methods show excellent performance for all these datasets across all the metrics. Source code: https://github.com/ayu987/deep-regression-unlearning

Author Information

Ayush Tarun (Mavvex Labs)
Ayush Tarun

I am deeply captivated by the transformative potential of deep learning and machine learning across diverse domains. My experience spans recommendation systems, computer vision, natural language processing (NLP), and privacy. At present, my research primarily focuses on privacy and security, explainability, and fairness in deep learning.

Vikram Chundawat (BITS Pilani, BITS Pilani)
Murari Mandal (KIIT Bhubaneswar India)
Murari Mandal

My current research is in machine unlearning, data valuation, synthetic data generation, and deep learning.

Mohan Kankanhalli (National University of Singapore,)

More from the Same Authors