Imagen de Portada

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Zhuo, Wang, Qizhou, Hong, Ziming, Ye, Shanshan, Han, Bo, Liu, Tongliang
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
por: Yang, Puning, et al.
Publicado: (2025)

Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning
por: Taheri, Ali, et al.
Publicado: (2025)

MeGU: Machine-Guided Unlearning with Target Feature Disentanglement
por: Wang, Haoyu, et al.
Publicado: (2026)

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
por: Wang, Qizhou, et al.
Publicado: (2024)

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
por: Lin, Runqi, et al.
Publicado: (2023)

Ascent Fails to Forget
por: Mavrothalassitis, Ioannis, et al.
Publicado: (2025)

Label Smoothing Improves Gradient Ascent in LLM Unlearning
por: Pang, Zirui, et al.
Publicado: (2025)

AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
por: Hong, Ziming, et al.
Publicado: (2025)

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
por: Wang, Qizhou, et al.
Publicado: (2025)

Machine Unlearning for Streaming Forgetting
por: Shen, Shaofei, et al.
Publicado: (2025)

CUFG: Curriculum Unlearning Guided by the Forgetting Gradient
por: Miao, Jiaxing, et al.
Publicado: (2025)

Machine Unlearning under Retain-Forget Entanglement
por: Cheng, Jingpu, et al.
Publicado: (2026)

Explainable LLM Unlearning Through Reasoning
por: Liao, Junfeng, et al.
Publicado: (2026)

Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
por: Dolgova, Polina, et al.
Publicado: (2026)

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
por: Wei, Rongzhe, et al.
Publicado: (2025)

Forgetting Similar Samples: Can Machine Unlearning Do it Better?
por: Xu, Heng, et al.
Publicado: (2026)

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
por: Wang, Yue, et al.
Publicado: (2025)

LLM Unlearning with LLM Beliefs
por: Li, Kemou, et al.
Publicado: (2025)

Improved Localized Machine Unlearning Through the Lens of Memorization
por: Torkzadehmahani, Reihaneh, et al.
Publicado: (2024)

Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning
por: Liu, Yezi, et al.
Publicado: (2025)

Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment?
por: Yang, Hongzheng, et al.
Publicado: (2025)

Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural Networks
por: Melamed, Odelia, et al.
Publicado: (2025)

Towards Aligned Data Forgetting via Twin Machine Unlearning
por: Niu, Zhenxing, et al.
Publicado: (2025)

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
por: Fan, Chongyu, et al.
Publicado: (2024)

Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage
por: Rashid, Md Rafi Ur, et al.
Publicado: (2024)

Fine-Grained Gradient Restriction: A Simple Approach for Mitigating Catastrophic Forgetting
por: Liu, Bo, et al.
Publicado: (2024)

Toward Robust Non-Transferable Learning: A Survey and Benchmark
por: Hong, Ziming, et al.
Publicado: (2025)

Re-understanding Graph Unlearning through Memorization
por: Ding, Pengfei, et al.
Publicado: (2026)

When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
por: Hong, Ziming, et al.
Publicado: (2025)

Towards Reliable Forgetting: A Survey on Machine Unlearning Verification
por: Xue, Lulu, et al.
Publicado: (2025)

Governing AI Forgetting: Auditing for Machine Unlearning Compliance
por: Lin, Qinqi, et al.
Publicado: (2026)

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
por: Yang, Puning, et al.
Publicado: (2026)

When to Forget? Complexity Trade-offs in Machine Unlearning
por: Van Waerebeke, Martin, et al.
Publicado: (2025)

Towards Understanding Valuable Preference Data for Large Language Model Alignment
por: Zhang, Zizhuo, et al.
Publicado: (2025)

BrokenBind: Universal Modality Exploration beyond Dataset Boundaries
por: Huang, Zhuo, et al.
Publicado: (2026)

Variance-Reduced $(\varepsilon,δ)-$Unlearning using Forget Set Gradients
por: Van Waerebeke, Martin, et al.
Publicado: (2026)

Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion
por: Laguna, Sonia, et al.
Publicado: (2026)

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
por: Huang, Tao, et al.
Publicado: (2024)

Machine Unlearning using Forgetting Neural Networks
por: Hatua, Amartya, et al.
Publicado: (2024)

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
por: Chien, Eli, et al.
Publicado: (2024)