Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion

TL;DR

This paper introduces TFER, a novel continual unlearning framework that preserves decision boundaries for OOD detection by transforming target classes into OOD samples using free energy principles, enabling efficient and stable model updates.

Contribution

The paper proposes a boundary-preserving unlearning method based on free energy repulsion, addressing the geometric contradiction between OOD detection and class unlearning.

Findings

TFER achieves precise unlearning with minimal performance loss.

The Push-Pull mechanism enhances model stability and resistance to catastrophic forgetting.

Extensive experiments validate the effectiveness of TFER in continual unlearning scenarios.

Abstract

Deploying trustworthy AI in open-world environments faces a dual challenge: the necessity for robust Out-of-Distribution (OOD) detection to ensure system safety, and the demand for flexible machine unlearning to satisfy privacy compliance and model rectification. However, this objective encounters a fundamental geometric contradiction: current OOD detectors rely on a static and compact data manifold, whereas traditional classification-oriented unlearning methods disrupt this delicate structure, leading to a catastrophic loss of the model's capability to discriminate anomalies while erasing target classes. To resolve this dilemma, we first define the problem of boundary-preserving class unlearning and propose a pivotal conceptual shift: in the context of OOD detection, effective unlearning is mathematically equivalent to transforming the target class into OOD samples. Based on this, we propose the TFER (Total Free Energy Repulsion) framework. Inspired by the free energy principle, TFER constructs a novel Push-Pull game mechanism: it anchors retained classes within a low-energy ID manifold through a pull mechanism, while actively expelling forgotten classes to high-energy OOD regions using a free energy repulsion force. This approach is implemented via parameter-efficient fine-tuning, circumventing the prohibitive cost of full retraining. Extensive experiments demonstrate that TFER achieves precise unlearning while maximally preserving the model's discriminative performance on remaining classes and external OOD data. More importantly, our study reveals that the unique Push-Pull equilibrium of TFER endows the model with inherent structural stability, allowing it to effectively resist catastrophic forgetting without complex additional constraints, thereby demonstrating exceptional potential in continual unlearning tasks.