Related papers: A New Method for Avoiding Data Disclosure While Au…
Person re-identification (Re-ID) is a critical technique in the video surveillance system, which has achieved significant success in the supervised setting. However, it is difficult to directly apply the supervised model to arbitrary unseen…
Multimodal learning, which aims to understand and analyze information from multiple modalities, has achieved substantial progress in the supervised regime in recent years. However, the heavy dependence on data paired with expensive human…
Label distribution learning (LDL) provides a framework wherein a distribution over categories rather than a single category is predicted, with the aim of addressing ambiguity in labeled data. Existing research on LDL mainly focuses on the…
Semantic segmentation of various tissue and nuclei types in histology images is fundamental to many downstream tasks in the area of computational pathology (CPath). In recent years, Deep Learning (DL) methods have been shown to perform well…
The Minimum Description Length (MDL) principle selects the model that has the shortest code for data plus model. We show that for a countable class of models, MDL predictions are close to the true distribution in a strong sense. The result…
We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation of the continuous latent variables without having to use a…
The paper deals with models in which the dependent variable, some explanatory variables, or both represent sensitive data. We introduce a novel discretization method that preserves data privacy when working with such variables. A multiple…
Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones. We cast SSL…
Disclosure avoidance (DA) systems are used to safeguard the confidentiality of data while allowing it to be analyzed and disseminated for analytic purposes. These methods, e.g., cell suppression, swapping, and k-anonymity, are commonly…
Effective suppression of surface-related multiples is essential to prevent imaging artifacts and erroneous structural interpretations. While conventional approaches rely on accurate priors or subsurface model knowledge, and supervised…
Background: In the context of ongoing debate over data confidentiality versus shared use of research data, as raised following the new EU General Data Protection Regulation, we seek to find alternate techniques that can balance these two…
This paper presents a novel approach to classical linear regression, enabling model computation from data streams or in a distributed setting while preserving data privacy in federated environments. We extend this framework to generalized…
Large language models (LLMs) are increasingly integrated into real-time machine learning applications, where safeguarding user privacy is paramount. Traditional differential privacy mechanisms often struggle to balance privacy and accuracy,…
Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…
Association rule mining is an important data-mining technique that finds interesting association among a large set of data items. Since it may disclose patterns and various kinds of sensitive knowledge that are difficult to find otherwise,…
Bayesian methods have proven themselves to be successful across a wide range of scientific problems and have many well-documented advantages over competing methods. However, these methods run into difficulties for two major and prevalent…
Most statistical agencies release randomly selected samples of Census microdata, usually with sample fractions under 10% and with other forms of statistical disclosure control (SDC) applied. An alternative to SDC is data synthesis, which…
Unsupervised clustering algorithm can effectively reduce the dimension of high-dimensional unlabeled data, thus reducing the time and space complexity of data processing. However, the traditional clustering algorithm needs to set the upper…
Hidden variable graphical models can sometimes imply constraints on the observable distribution that are more complex than simple conditional independence relations. These observable constraints can falsify assumptions of the model that…
High-dimensional data that evolve dynamically feature predominantly in the modern data era. As a partial response to this, recent years have seen increasing emphasis to address the dimensionality challenge. However, the non-static nature of…