Related papers: Anonymous Learning via Look-Alike Clustering: A Pr…
The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it…
We address the problem of cluster identity estimation in a hierarchical federated learning setting in which users work toward learning different tasks. To overcome the challenge of task heterogeneity, users need to be grouped in a way such…
The task of privacy-preserving face recognition (PPFR) currently faces two major unsolved challenges: (1) existing methods are typically effective only on specific face recognition models and struggle to generalize to black-box face…
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person…
Spectral clustering is a widely used algorithm to find clusters in networks. Several researchers have studied the stability of spectral clustering under local differential privacy with the additional assumption that the underlying networks…
Protecting user privacy is a major concern for many machine learning systems that are deployed at scale and collect from a diverse set of population. One way to address this concern is by collecting and releasing data labels in an…
We address the problem of learning linear system models from observing multiple trajectories from different system dynamics. This framework encompasses a collaborative scenario where several systems seeking to estimate their dynamics are…
Text-to-image diffusion models, such as Stable Diffusion, generate highly realistic images from text descriptions. However, the generation of certain content at such high quality raises concerns. A prominent issue is the accurate depiction…
Spectral clustering is a popular and versatile clustering method based on a relaxation of the normalised graph cut objective. Despite its popularity, however, there is no single agreed upon method for tuning the important scaling parameter,…
Collecting and labeling real datasets to train the person search networks not only requires a lot of time and effort, but also accompanies privacy issues. The weakly-supervised and unsupervised domain adaptation methods have been proposed…
With the widespread application of large language models (LLMs), user privacy protection has become a significant research topic. Existing privacy preference modeling methods often rely on large-scale user data, making effective privacy…
A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the group…
Sampling schemes are fundamental tools in statistics, survey design, and algorithm design. A fundamental result in differential privacy is that a differentially private mechanism run on a simple random sample of a population provides…
We are concerned with learning models that generalize well to different \emph{unseen} domains. We consider a worst-case formulation over data distributions that are near the source domain in the feature space. Only using training data from…
Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…
Although unsupervised person re-identification (Re-ID) has drawn increasing research attention recently, it remains challenging to learn discriminative features without annotations across disjoint camera views. In this paper, we address the…
Convex clustering, a convex relaxation of k-means clustering and hierarchical clustering, has drawn recent attentions since it nicely addresses the instability issue of traditional nonconvex clustering methods. Although its computational…
Open-set face recognition describes a scenario where unknown subjects, unseen during the training stage, appear on test time. Not only it requires methods that accurately identify individuals of interest, but also demands approaches that…
In the Mixup training paradigm, a model is trained using convex combinations of data points and their associated labels. Despite seeing very few true data points during training, models trained using Mixup seem to still minimize the…
The purpose of anonymizing structured data is to protect the privacy of individuals in the data while retaining the statistical properties of the data. An important class of attack on anonymized data is attribute inference, where an…