相关论文: MUSO: Achieving Exact Machine Unlearning in Over-P…

Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with…

Learned optimizers (LOs) have the potential to significantly reduce the wall-clock training time of neural networks. However, they can struggle to optimize unseen tasks (meta-generalize), especially when training networks wider than those…

With evolving data regulations, machine unlearning (MU) has become an important tool for fostering trust and safety in today's AI models. However, existing MU methods focusing on data and/or weight perspectives often suffer limitations in…

Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…

Machine learning algorithms have been used widely in various applications and areas. To fit a machine learning model into different problems, its hyper-parameters must be tuned. Selecting the best hyper-parameter configuration for machine…

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…

Recent generative models face significant risks of producing harmful content, which has underscored the importance of machine unlearning (MU) as a critical technique for eliminating the influence of undesired data. However, existing MU…

Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning…

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional…

This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models--a notably under-researched area.…

Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmarks rely on synthetic knowledge injection or complete subject-level deletion, which fail to…

A number of popular transfer learning methods rely on grid search to select regularization hyperparameters that control over-fitting. This grid search requirement has several key disadvantages: the search is computationally expensive,…

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good…

Automated machine learning aims to automate the whole process of machine learning, including model configuration. In this paper, we focus on automated hyperparameter optimization (HPO) based on sequential model-based optimization (SMBO).…

The imperative to eliminate undesirable data memorization underscores the significance of machine unlearning for large language models (LLMs). Recent research has introduced a series of promising unlearning methods, notably boosting the…

Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative…

Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to…

Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…

Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep neural networks…

Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model…