CVAILGApr 19, 2024

Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images

arXiv:2404.12922v126 citationsh-index: 4ECCV
Originality Incremental advance
AI Analysis

This addresses the challenge of efficient and privacy-preserving model updates in machine learning, offering a novel approach that eliminates the need for retain sets, which is incremental but practical for real-world applications.

The paper tackles the problem of machine unlearning without a retain set by introducing SCAR, which uses a modified Mahalanobis distance and distillation with out-of-distribution images to eliminate specific information while preserving test accuracy, achieving performance comparable to state-of-the-art methods that use retain sets on three public datasets.

In this paper, we introduce Selective-distillation for Class and Architecture-agnostic unleaRning (SCAR), a novel approximate unlearning method. SCAR efficiently eliminates specific information while preserving the model's test accuracy without using a retain set, which is a key component in state-of-the-art approximate unlearning algorithms. Our approach utilizes a modified Mahalanobis distance to guide the unlearning of the feature vectors of the instances to be forgotten, aligning them to the nearest wrong class distribution. Moreover, we propose a distillation-trick mechanism that distills the knowledge of the original model into the unlearning model with out-of-distribution images for retaining the original model's test performance without using any retain set. Importantly, we propose a self-forget version of SCAR that unlearns without having access to the forget set. We experimentally verified the effectiveness of our method, on three public datasets, comparing it with state-of-the-art methods. Our method obtains performance higher than methods that operate without the retain set and comparable w.r.t the best methods that rely on the retain set.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes