Related papers: Model-assisted and Knowledge-guided Transfer Regre…

A major problem of machine-learning approaches in structural dynamics is the frequent lack of structural data. Inspired by the recently-emerging field of population-based structural health monitoring (PBSHM), and the use of transfer…

Machine learning has emerged as a new tool in chemistry to bypass expensive experiments or quantum-chemical calculations, for example, in high-throughput screening applications. However, many machine learning studies rely on small data…

Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware. Distillation from a trained source model may represent a solution for the first but does not…

State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…

Heterogeneous data are now ubiquitous in many applications in which correctly identifying the subgroups from a heterogeneous population is critical. Although there is an increasing body of literature on subgroup detection, existing methods…

Collaborative learning through latent shared feature representations enables heterogeneous clients to train personalized models with improved performance and reduced sample complexity. Despite empirical success and extensive study, the…

Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for…

Automated learning of patients demographics can be seen as multi-label problem where a patient model is based on different race and gender groups. The resulting model can be further integrated into Privacy-Preserving Data Mining, where it…

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper…

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…

This paper addresses challenges in robust transfer learning stemming from ambiguity in Bayes classifiers and weak transferable signals between the target and source distribution. We introduce a novel quantity called the ''ambiguity level''…

In the financial risk domain, particularly in credit default prediction and fraud detection, accurate identification of high-risk class instances is paramount, as their occurrence can have significant economic implications. Although machine…

When the performance of a machine learning model varies over groups defined by sensitive attributes (e.g., gender or ethnicity), the performance disparity can be expressed in terms of the probability distributions of the input and output…

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…

Data fusion and transfer learning are rapidly growing fields that enhance model performance for a target population by leveraging other related data sources or tasks. The challenges lie in the various potential heterogeneities between the…

Transfer learning aims to improve performance on a target task by leveraging information from related source tasks. We propose a nonparametric regression transfer learning framework that explicitly models heterogeneity in the source-target…

In many practical data mining scenarios, such as network intrusion detection, Twitter spam detection, and computer-aided diagnosis, a source domain that is different from but related to a target domain is very common. In addition, a large…

Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer functions. Besides flexibility and accuracy, a key benefit of…

Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications. However, since they are highly data-driven, relying on billion-sized datasets randomly…

Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness. One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints.…