相关论文: Continual Forgetting for Pre-trained Vision Models

Machine unlearning is essential for meeting legal obligations such as the right to be forgotten, which requires the removal of specific data from machine learning models upon request. While several approaches to unlearning have been…

Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and correcting errors or…

We study the problem of unlearning datapoints from a learnt model. The learner first receives a dataset $S$ drawn i.i.d. from an unknown distribution, and outputs a model $\widehat{w}$ that performs well on unseen samples from the same…

Once users have shared their data online, it is generally difficult for them to revoke access and ask for the data to be deleted. Machine learning (ML) exacerbates this problem because any model trained with said data may have memorized it,…

We propose a novel regularization-based continual learning method, dubbed as Adaptive Group Sparsity based Continual Learning (AGS-CL), using two group sparsity-based penalties. Our method selectively employs the two penalties when learning…

Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate…

Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and learn new tasks…

Deep neural networks are known to suffer the catastrophic forgetting problem, where they tend to forget the knowledge from the previous tasks when sequentially learning new tasks. Such failure hinders the application of deep learning based…

Machine unlearning (MU) is becoming a promising paradigm to achieve the "right to be forgotten", where the training trace of any chosen data points could be eliminated, while maintaining the model utility on general testing samples after…

Continual learning (CL) aims to develop techniques by which a single model adapts to an increasing number of tasks encountered sequentially, thereby potentially leveraging learnings across tasks in a resource-efficient manner. A major…

Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words. Several efforts in the literature have shown that sparsity is key to enabling a good…

Continual learning for vision-language models has achieved remarkable performance through synthetic replay, where samples are generated using Stable Diffusion to regularize during finetuning and retain knowledge. However, real-world…

Vision-Brain Understanding (VBU) aims to extract visual information perceived by humans from brain activity recorded through functional Magnetic Resonance Imaging (fMRI). Despite notable advancements in recent years, existing studies in VBU…

Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspective for MU is presented upon low-dimensional feature…

Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically modify model parameters, but such updates can be unstable,…

Modern privacy regulations grant citizens the right to be forgotten by products, services and companies. In case of machine learning (ML) applications, this necessitates deletion of data not only from storage archives but also from ML…

Efficient continual learning techniques have been a topic of significant research over the last few years. A fundamental problem with such learning is severe degradation of performance on previously learned tasks, known also as catastrophic…

Transformer based diffusion and vision-language models have achieved remarkable success; yet, efficiently removing undesirable or sensitive information without retraining remains a central challenge for model safety and compliance. We…

Traditional patch-based sparse representation modeling of natural images usually suffer from two problems. First, it has to solve a large-scale optimization problem with high computational complexity in dictionary learning. Second, each…

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…