Related papers: TRU: Targeted Reverse Update for Efficient Multimo…

Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local editing problem; in min-max unlearning, the key local object is…

Machine unlearning aims to remove the influence of a designated forget set from a trained model while preserving utility on the retained data. In modern deep networks, approximate unlearning frequently fails under large or adversarial…

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. While extensive research has focused on developing efficient unlearning…

Modern recommender systems powered by Graph Neural Networks (GNNs) excel at modeling complex user-item interactions, yet increasingly face scenarios requiring selective forgetting of training data. Beyond user requests to remove specific…

Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction…

People break up, miscarry, and lose loved ones. Their online streaming and shopping recommendations, however, do not necessarily update, and may serve as unhappy reminders of their loss. When users want to renege on their past actions, they…

As a new and promising approach, existing machine unlearning (MU) works typically emphasize theoretical formulations or optimization objectives to achieve knowledge removal. However, when deployed in real-world scenarios, such solutions…

The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Fine-Grained Change Detection and Regression Analysis are essential in many applications of ArtificialIntelligence. In practice, this task is often challenging owing to the lack of reliable ground truth information andcomplexity arising…

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender…

The goal of unbiased learning to rank (ULTR) is to leverage implicit user feedback for optimizing learning-to-rank systems. Among existing solutions, automatic ULTR algorithms that jointly learn user bias models (i.e., propensity models)…

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,…

Metal artefact reduction (MAR) techniques aim at removing metal-induced noise from clinical images. In Computed Tomography (CT), supervised deep learning approaches have been shown effective but limited in generalisability, as they mostly…

Machine unlearning is the process of efficiently removing specific information from a trained machine learning model without retraining from scratch. Existing unlearning methods, which often provide provable guarantees, typically involve…

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…

With the introduction of data protection and privacy regulations, it has become crucial to remove the lineage of data on demand from a machine learning (ML) model. In the last few years, there have been notable developments in machine…

As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data.…

This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals. In contrast to conventional visual instruction tuning approaches that…