Summary of Geniu: a Restricted Data Access Unlearning For Imbalanced Data, by Chenhao Zhang et al.
GENIU: A Restricted Data Access Unlearning for Imbalanced Data
by Chenhao Zhang, Shaofei Shen, Yawen Zhao, Weitong Tony Chen, Miao Xu
First submitted to arxiv on: 12 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A machine learning framework called GENerative Imbalanced Unlearning (GENIU) is proposed to address class unlearning with restricted data access and imbalanced original data. The GENIU framework utilizes a Variational Autoencoder (VAE) to train a proxy generator alongside the original model, generating accurate proxies for each class that can be used in the unlearning phase without relying on the original training data. To further mitigate performance degradation when forgetting the majority class, an in-batch tuning strategy is introduced. GENIU is the first practical framework for class unlearning in imbalanced data settings and restricted data access, ensuring the preservation of essential information for future unlearning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Class unlearning with machine learning as a service (MLaaS) is important because classification tasks account for most MLaaS applications. A common approach to class unlearning involves retraining the model on the original data, excluding the data to be forgotten. However, this method requires access to the original training data, which is not always available. GENIU is a new framework that addresses this issue by generating proxies using a VAE and leveraging these proxies in the unlearning phase. |
Keywords
» Artificial intelligence » Classification » Machine learning » Variational autoencoder
