Imagen de Portada

Model Sparsity Can Simplify Machine Unlearning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jia, Jinghan, Liu, Jiancheng, Ram, Parikshit, Yao, Yuguang, Liu, Gaowen, Liu, Yang, Sharma, Pranay, Liu, Sijia
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
por: Jia, Jinghan, et al.
Publicado: (2024)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
por: Chen, Yiwei, et al.
Publicado: (2025)

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
por: Sun, Changchang, et al.
Publicado: (2024)

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
por: Wang, Changsheng, et al.
Publicado: (2025)

Label Smoothing Improves Machine Unlearning
por: Di, Zonglin, et al.
Publicado: (2024)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
por: Wang, Changsheng, et al.
Publicado: (2025)

Rethinking Machine Unlearning for Large Language Models
por: Liu, Sijia, et al.
Publicado: (2024)

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
por: Zhuang, Haomin, et al.
Publicado: (2024)

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
por: Zhang, Yihua, et al.
Publicado: (2024)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
por: Fan, Chongyu, et al.
Publicado: (2024)

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
por: Jia, Jinghan, et al.
Publicado: (2024)

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

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
por: Pan, Zhuoshi, et al.
Publicado: (2023)

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
por: Lang, Yicheng, et al.
Publicado: (2025)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
por: Fan, Chongyu, et al.
Publicado: (2023)

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
por: Fan, Chongyu, et al.
Publicado: (2025)

LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
por: Wang, Changsheng, et al.
Publicado: (2025)

Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
por: Gu, Renjie, et al.
Publicado: (2026)

DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
por: Chen, Aochuan, et al.
Publicado: (2023)

BLUR: A Bi-Level Optimization Approach for LLM Unlearning
por: Reisizadeh, Hadi, et al.
Publicado: (2025)

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
por: Chen, Yiwei, et al.
Publicado: (2025)

Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
por: Fan, Chongyu, et al.
Publicado: (2026)

SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution
por: Wang, Yuze, et al.
Publicado: (2026)

Adversarial Machine Unlearning
por: Di, Zonglin, et al.
Publicado: (2024)

Large Language Model Unlearning
por: Yao, Yuanshun, et al.
Publicado: (2023)

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation
por: Jia, Jinghan, et al.
Publicado: (2025)

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
por: Zhong, Yisheng, et al.
Publicado: (2026)

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
por: Pal, Soumyadeep, et al.
Publicado: (2024)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
por: Zhang, Mohan, et al.
Publicado: (2025)

Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity
por: Zhao, Jinze, et al.
Publicado: (2024)

Prompt Diffusion Robustifies Any-Modality Prompt Learning
por: Du, Yingjun, et al.
Publicado: (2024)

Attention Smoothing Is All You Need For Unlearning
por: Zade, Saleh Zare, et al.
Publicado: (2026)

Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
por: Yao, Yuguang, et al.
Publicado: (2023)

Unlink to Unlearn: Simplifying Edge Unlearning in GNNs
por: Tan, Jiajun, et al.
Publicado: (2024)

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

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
por: Shang, Bingqi, et al.
Publicado: (2025)

Compositional Program Generation for Few-Shot Systematic Generalization
por: Klinger, Tim, et al.
Publicado: (2023)

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
por: Sun, Yuhao, et al.
Publicado: (2025)

Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
por: Reisizadeh, Hadi, et al.
Publicado: (2025)

Efficient Calibration for Decision Making
por: Gopalan, Parikshit, et al.
Publicado: (2025)