paper-with-me

홈 › Papers

SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness

2024-03-13 · Sangamesh Kodge, Deepak Ravikumar, Gobinda Saha, Kaushik Roy

Label corruption, where training samples are mislabeled due to non-expert annotation or adversarial attacks, significantly degrades model performance. Acquiring large, perfectly labeled datasets is costly, and retraining models from scratch is computationally expensive. To address this, we introduce Scaled Activation Projection (SAP), a novel SVD (Singular Value Decomposition)-based corrective machine unlearning algorithm. SAP mitigates label noise by identifying a small subset of trusted samples using cross-entropy loss and projecting model weights onto a clean activation space estimated using SVD on these trusted samples. This process suppresses the noise introduced in activations due to the mislabeled samples. In our experiments, we demonstrate SAP's effectiveness on synthetic noise with different settings and real-world label noise. SAP applied to the CIFAR dataset with 25% synthetic corruption show upto 6% generalization improvements. Additionally, SAP can improve the generalization over noise robust training approaches on CIFAR dataset by ~3.2% on average. Further, we observe generalization improvements of 2.31% for a Vision Transformer model trained on naturally corrupted Clothing1M.

📄 PDF Abstract BibTeX arXiv:2403.08618

Code (1)

sangamesh-kodge/sap 공식 구현 pytorch

Tasks

Machine Unlearning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Corrective Machine Unlearning

2024-02-21 · Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru 외

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipul…

Machine Unlearning

Neural Corrective Machine Unranking

2024-11-13 · Jingrui Hou, Axel Finke, Georgina Cosma

Machine unlearning in neural information retrieval (IR) systems requires removing specific data whilst maintaining model performance. Applying existing machine unlearning methods to IR may compromise retrieval effectiven…

Information RetrievalMachine UnlearningRetrieval

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection

2025-08-21 · Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong 외 arxiv

While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowled…

A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks

2024-12-01 · Varshita Kolipaka, Akshit Sinha, Debangan Mishra, Sumit Kumar 외

Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distributed (i.i.d.) assumption, adversarial m…

Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic

2025-11-24 · Mostafa Mozafari, Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri arxiv

Corrupted training data are ubiquitous. Corrective Machine Unlearning (CMU) seeks to remove the influence of such corruption post-training. Prior CMU typically assumes access to identified corrupted training samples (a "…