相关论文: TRU: Targeted Reverse Update for Efficient Multimo…

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize…

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially…

We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch. LoTUS smooths the prediction probabilities of the model up to an…

Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model…

Data privacy and security have become a non-negligible factor in load forecasting. Previous researches mainly focus on training stage enhancement. However, once the model is trained and deployed, it may need to `forget' (i.e., remove the…

Multimodal federated learning in real-world settings often encounters incomplete and heterogeneous data across clients. This results in misaligned local feature representations that limit the effectiveness of model aggregation. Unlike prior…

Machine unlearning is the problem of removing the effect of a subset of training data (the ''forget set'') from a trained model without damaging the model's utility e.g. to comply with users' requests to delete their data, or remove…

Rewards serve as a measure of user satisfaction and act as a limiting factor in interactive recommender systems. In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning. Previous…

Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions.…

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task…

Learning user preferences for products based on their past purchases or reviews is at the cornerstone of modern recommendation engines. One complication in this learning task is that some users are more likely to purchase products or review…

Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centres on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts…

Practical recommender systems need be periodically retrained to refresh the model with new interaction data. To pursue high model fidelity, it is usually desirable to retrain the model on both historical and new data, since it can account…

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 manipulated or incorrect.…

Click-through rate (CTR) prediction serves as a cornerstone of recommender systems. Despite the strong performance of current CTR models based on user behavior modeling, they are still severely limited by interaction sparsity, especially in…

Machine unlearning aims to selectively remove targeted knowledge from Large Language Models (LLMs), ensuring they forget specified content while retaining essential information. Existing unlearning metrics assess whether a model correctly…

Traffic allocation is a process of redistributing natural traffic to products by adjusting their positions in the post-search phase, aimed at effectively fostering merchant growth, precisely meeting customer demands, and ensuring the…