Papers with Code 아카이브

Machine Unlearning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/wangln19/vertical-federated-unlearning

공식 코드

Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning

https://github.com/wrh14/deep_unlearning

공식 코드

Evaluating Deep Unlearning in Large Language Models

https://github.com/wujcan/gif-torch

공식 코드

GIF: A General Graph Unlearning Strategy via Influence Function

https://github.com/wwq5-code/scu

공식 코드

SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications

https://github.com/xiao-jian-zi/mu-goldfish-an-efficient-federated-unlearning-framework

공식 코드

Goldfish: An Efficient Federated Unlearning Framework

https://github.com/xiaoyuxu1/representational_analysis_tools

공식 코드

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs

https://github.com/xiye7lai/cure4rec

공식 코드

CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence

https://github.com/xkli-allen/megu

공식 코드

Towards Effective and General Graph Unlearning via Mutual Evolution

https://github.com/xlab-hub/cause

공식 코드

Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices

https://github.com/xuwkk/task_aware_machine_unlearning

공식 코드

Task-Aware Machine Unlearning and Its Application in Load Forecasting

https://github.com/yaojin17/unlearning_llm

공식 코드

Machine Unlearning of Pre-trained Large Language Models

https://github.com/yongliang-wu/doco

공식 코드

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient

https://github.com/yongliang-wu/unlearn-DoCoPreG

공식 코드

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient

https://github.com/yuyangxueed/reconunlearning

공식 코드

Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction

https://github.com/z1zs/mmunlearner

공식 코드

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

https://github.com/zhangbinchi/certified-deep-unlearning

공식 코드

Towards Certified Unlearning for Deep Neural Networks

https://github.com/zhangbinchi/unlearning-verification-is-fragile

공식 코드

Verification of Machine Unlearning is Fragile

https://github.com/zhliu0106/learning-to-refuse

공식 코드

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs

https://github.com/zibinpan/mollm

공식 코드

Multi-Objective Large Language Model Unlearning

https://github.com/zzwjames/failurellmunlearning

공식 코드

Catastrophic Failure of LLM Unlearning via Quantization

https://version.helsinki.fi/mahadeva/unlearning-experiments

공식 코드

Certifiable Machine Unlearning for Linear Models

https://github.com/AIM-Intelligence/Automated-Multi-Turn-Jailbreaks

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

https://github.com/ChrisWaites/data-deletion

Machine Unlearning

https://github.com/ChrisWaites/descent-to-delete

Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

https://github.com/FaceOnLive/Face-Recognition-SDK-Android

Continual Forgetting for Pre-trained Vision Models

https://github.com/Recognito-Vision/Face-SDK-Linux-Demos

Continual Forgetting for Pre-trained Vision Models

https://github.com/RhincodonE/Privacy-Onion-effect

The Privacy Onion Effect: Memorization is Relative

https://github.com/jjbrophy47/dare

Machine Unlearning for Random Forests

https://github.com/k1nght/unified-unlearning-w-remain-geometry

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

https://github.com/locuslab/open-unlearning

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

https://github.com/meghdadk/SCRUB

Towards Adversarial Evaluations for Inexact Machine Unlearning

https://github.com/somvy/multimodal_unlearning

CLEAR: Character Unlearning in Textual and Visual Modalities

https://github.com/swj0419/detect-pretrain-code

Detecting Pretraining Data from Large Language Models

https://github.com/swj0419/muse_bench

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.