Related papers: LEGATO: Good Identity Unlearning Is Continuous

Machine learning models, especially deep models, may unintentionally remember information about their training data. Malicious attackers can thus pilfer some property about training data by attacking the model via membership inference…

The ability of intelligent agents to learn and remember multiple tasks sequentially is crucial to achieving artificial general intelligence. Many continual learning (CL) methods have been proposed to overcome catastrophic forgetting which…

Unified Multimodal Generative Models (UMGMs) unify visual understanding and image generation within a single autoregressive framework. However, their ability to continually learn new tasks is severely hindered by catastrophic forgetting,…

As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge when adapting to new tasks, resulting in severe performance…

Federated Unlearning (FU) aims to efficiently remove the influence of specific client data from a federated model while preserving utility for the remaining clients. However, three key challenges remain: (1) existing unlearning objectives…

Training machine learning models requires the storage of large datasets, which often contain sensitive or private data. Storing data is associated with a number of potential risks which increase over time, such as database breaches and…

Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining dataset. Existing MUL research involves fine-tuning using a…

Machine learning and data systems increasingly function as infrastructures of memory: they ingest, store, and operationalize traces of personal, political, and cultural life. Yet contemporary governance demands credible forms of forgetting,…

Machine unlearning is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove harmful or corrupted training samples. Despite this, most existing methods tackle the problem purely from a…

As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques. Many existing unlearning methods aim to suppress…

Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks…

Training a neural network model can be a lifelong learning process and is a computationally intensive one. A severe adverse effect that may occur in deep neural network models is that they can suffer from catastrophic forgetting during…

Machine unlearning (MU) aims to eliminate information that has been learned from specific training data, namely forgetting data, from a pre-trained model. Currently, the mainstream of existing MU methods involves modifying the forgetting…

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more…

As Large Language Models (LLMs) demonstrate extensive capability in learning from documents, LLM unlearning becomes an increasingly important research area to address concerns of LLMs in terms of privacy, copyright, etc. A conventional LLM…

Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-scale training data inevitably raises concerns about privacy,…

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine…

Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer needed, freeing up capacity to learn. Weight decay, viewed as a…

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead…

Large language models (LLMs) risk retaining unauthorized or sensitive information from their training data, which raises privacy concerns. LLM unlearning seeks to mitigate these risks by selectively removing specified data while maintaining…