相关论文: SoK: Data Minimization in Machine Learning

Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generations wireless systems. This led to a large body of research work that applies ML techniques to solve problems in different layers of the…

The Minimum Description Length (MDL) principle is solidly based on a provably ideal method of inference using Kolmogorov complexity. We test how the theory behaves in practice on a general problem in model selection: that of learning the…

Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD]…

Money laundering is a financial crime that obscures the origin of illicit funds, necessitating the development and enforcement of anti-money laundering (AML) policies by governments and organizations. The proliferation of mobile payment…

Recent years have witnessed a surge in deep learning research, marked by the introduction of expansive generative models like OpenAI's SORA and GPT, Meta AI's LLAMA series, and Google's FLAN, BART, and Gemini models. However, the rapid…

In the realm of real-world devices, centralized servers in Federated Learning (FL) present challenges including communication bottlenecks and susceptibility to a single point of failure. Additionally, contemporary devices inherently exhibit…

Model-based paradigms for decision-making and control are becoming ubiquitous in robotics. They rely on the ability to efficiently learn a model of the system from data. Structured Mechanical Models (SMMs) are a data-efficient black-box…

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and…

Continuous Integration (CI) has become a well-established software development practice for automatically and continuously integrating code changes during software development. An increasing number of Machine Learning (ML) based approaches…

Schema matching (SM) and entity matching (EM) tasks are crucial for data integration. While large language models (LLMs) have shown promising results in these tasks, they suffer from hallucinations and confusion about task instructions.…

Data mining is the way toward mining fascinating patterns or information from an enormous level of the database. Data mining additionally opens another risk to privacy and data security.One of the maximum significant themes in the research…

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used…

Privacy-preserving machine learning (ML) seeks to balance data utility and privacy, especially as regulations like the GDPR mandate the anonymization of personal data for ML applications. Conventional anonymization approaches often reduce…

Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of…

Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the training of accurate neural models. Its applications span…

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…

Knowledge distillation has emerged as a powerful technique for compressing large language models (LLMs) into efficient, deployable architectures while preserving their advanced capabilities. Recent advances in low-rank knowledge…

Dynamic Mode Decomposition (DMD) and its variants, such as extended DMD (EDMD), are broadly used to fit simple linear models to dynamical systems known from observable data. As DMD methods work well in several situations but perform poorly…

State-of-the-art neural networks can be trained to become remarkable solutions to many problems. But while these architectures can express symbolic, perfect solutions, trained models often arrive at approximations instead. We show that the…

Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage, has become a well-accepted standard for privacy protection. Combined with powerful machine learning techniques, differentially private machine…