paper-with-me

Papers

Reference-Guided Machine Unlearning

2026-03-11 · Jonas Mirlach, Sonia Laguna, Julia E. Vogt arxiv

Machine unlearning aims to remove the influence of specific data from trained models while preserving general utility. Existing approximate unlearning methods often rely on performance-degradation heuristics, such as loss maximization or random labeling. However, these signals can be poorly conditioned, leading to unstable optimization and harming the model's generalization. We argue that unlearning should instead prioritize distributional indistinguishability, aligning the model's behavior on forget data with its behavior on truly unseen data. Motivated by this, we propose Reference-Guided Unlearning (ReGUn), a framework that leverages a disjoint held-out dataset to provide a principled, class-conditioned reference for distillation. We demonstrate across various model architectures, natural image datasets, and varying forget fractions that ReGUn consistently outperforms standard approximate baselines, achieving a superior forgetting-utility trade-off.

📄 PDF Abstract BibTeX arXiv:2603.11210

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models

2026-04-15 · Wenxuan Li, Zhenfei Zhang, Mi Zhang, Geng Hong 외 arxiv

Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has emerged as a potential remedy, prevailing paradigms rely on user-pr…

Cross-Modal Attention Guided Unlearning in Vision-Language Models

2025-10-08 · Karuna Bhaila, Aneesh Komanduri, Minh-Hao Van, Xintao Wu arxiv

Vision-Language Models (VLMs) have demonstrated immense capabilities in multi-modal understanding and inference tasks such as Visual Question Answering (VQA), which requires models to infer outputs based on visual and te…

Visual Question Answering

WSS-CL: Weight Saliency Soft-Guided Contrastive Learning for Efficient Machine Unlearning Image Classification

2025-08-06 · Thang Duc Tran, Thai Hoang Le arxiv

Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primarily on data-centric or weight-based stra…

Contrastive LearningImage Classification

Distribution-Guided and Constrained Quantum Machine Unlearning

2026-01-07 · Nausherwan Malik, Zubair Khalid, Muhammad Faryad arxiv

Machine unlearning aims to remove the influence of specific training data from a learned model without full retraining. While recent work has begun to explore unlearning in quantum machine learning, existing approaches l…

Quantum Machine Learning

Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint

2025-08-28 · Zhihao Liu, Jian Lou, Yuke Hu, Xiaochen Li 외 arxiv

Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request the removal of their data from trained …