Image de couverture de livre

SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Yuze, Tong, Yujia, Liu, Xuan, Dong, Junhao
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels
par: Tong, Yujia, et autres
Publié: (2025)

Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks
par: Zhang, Tian, et autres
Publié: (2026)

LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning
par: Tong, Yujia, et autres
Publié: (2025)

Model Sparsity Can Simplify Machine Unlearning
par: Jia, Jinghan, et autres
Publié: (2023)

Controllable Machine Unlearning via Gradient Pivoting
par: Hwang, Youngsik, et autres
Publié: (2025)

ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
par: Liu, Hongyi, et autres
Publié: (2025)

MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs
par: Sun, Yan, et autres
Publié: (2025)

RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning
par: Hu, Junhao, et autres
Publié: (2025)

Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
par: Li, Guanchen, et autres
Publié: (2025)

Targeted Unlearning with Single Layer Unlearning Gradient
par: Cai, Zikui, et autres
Publié: (2024)

On the Identifiability of Nonlinear ICA: Sparsity and Beyond
par: Zheng, Yujia, et autres
Publié: (2022)

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
par: Hu, Shengyuan, et autres
Publié: (2024)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
par: Deng, Kaiyuan, et autres
Publié: (2026)

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
par: Chien, Eli, et autres
Publié: (2024)

QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs
par: Mishra, Himanshu, et autres
Publié: (2026)

StructSynth: Leveraging LLMs for Structure-Aware Tabular Data Synthesis in Low-Data Regimes
par: Liu, Siyi, et autres
Publié: (2025)

Certified Machine Unlearning via Noisy Stochastic Gradient Descent
par: Chien, Eli, et autres
Publié: (2024)

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
par: Wang, Yaxuan, et autres
Publié: (2025)

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
par: Yin, Lu, et autres
Publié: (2023)

Improving Decision Sparsity
par: Sun, Yiyang, et autres
Publié: (2024)

Uncertainty-Aware Token Importance Estimation in Spiking Transformers
par: Liu, Wenxuan, et autres
Publié: (2026)

LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models
par: Su, Yupeng, et autres
Publié: (2024)

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
par: Huang, Zhuo, et autres
Publié: (2026)

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
par: Chen, Yiwei, et autres
Publié: (2025)

Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation
par: Sundaram, Ganesh, et autres
Publié: (2026)

Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction
par: Tong, Yujia, et autres
Publié: (2025)

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
par: Lin, Shen, et autres
Publié: (2026)

MPRU: Modular Projection-Redistribution Unlearning as Output Filter for Classification Pipelines
par: Peng, Minyi, et autres
Publié: (2025)

Sparsity-Aware Evolution for Model Merging
par: Zhang, Huan, et autres
Publié: (2026)

LLM Unlearning via Loss Adjustment with Only Forget Data
par: Wang, Yaxuan, et autres
Publié: (2024)

Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation
par: Guo, Qi, et autres
Publié: (2024)

Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts
par: Dong, Yuze, et autres
Publié: (2026)

Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?
par: Haruna, Yunusa, et autres
Publié: (2026)

Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformation
par: Zhang, He, et autres
Publié: (2024)

R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
par: Zhang, Zhenyu, et autres
Publié: (2025)

Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking
par: Sun, Weixiang, et autres
Publié: (2024)

CUFG: Curriculum Unlearning Guided by the Forgetting Gradient
par: Miao, Jiaxing, et autres
Publié: (2025)

Descend or Rewind? Stochastic Gradient Descent Unlearning
par: Mu, Siqiao, et autres
Publié: (2025)

Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-Gradients
par: Mora, Alessio, et autres
Publié: (2025)

Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
par: Yang, Hui, et autres
Publié: (2026)