Related papers: HUGO-CS: A Hybrid-Labeled, Uncertainty-Aware, Gene…
Positive-Unlabeled (PU) learning aims to learn a model with rare positive samples and abundant unlabeled samples. Compared with classical binary classification, the task of PU learning is much more challenging due to the existence of many…
Currently, the in-context learning method based on large language models (LLMs) has become the mainstream of text-to-SQL research. Previous works have discussed how to select demonstrations related to the user question from a human-labeled…
The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, unmeasured variables, such as confounders, break this…
Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users. Existing RS benchmark datasets primarily focus on the exposure space, where…
The use of user/product information in sentiment analysis is important, especially for cold-start users/products, whose number of reviews are very limited. However, current models do not deal with the cold-start problem which is typical in…
Zero-shot hyperparameter optimization (HPO) is a simple yet effective use of transfer learning for constructing a small list of hyperparameter (HP) configurations that complement each other. That is to say, for any given dataset, at least…
The X-ray regime, where the most massive visible component of galaxy clusters, the intra cluster medium (ICM), is visible, offers directly measured quantities, like the luminosity, and derived quantities, like the total mass, to…
This paper proposes a Federated Learning Code Smell Detection (FedCSD) approach that allows organizations to collaboratively train federated ML models while preserving their data privacy. These assertions have been supported by three…
Human-robot collaboration (HRC) is a key focus of Industry 5.0, aiming to enhance worker productivity while ensuring well-being. The ability to perceive human psycho-physical states, such as stress and cognitive load, is crucial for…
We analyze the clustering of galaxies in the first public data release of the HSC Subaru Strategic Program. Despite the relatively small footprints of the observed fields, the data are an excellent proxy for the deep photometric datasets…
We present the design and methods of the COS-Halos survey, a systematic investigation of the gaseous halos of 44 z = 0.15-0.35 galaxies using background QSOs observed with the Cosmic Origins Spectrograph aboard the Hubble Space Telescope.…
This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…
We consider here a classification method that balances two objectives: large similarity within the samples in the cluster, and large dissimilarity between the cluster and its complement. The method, referred to as HNC or SNC, requires seed…
Virtual staining of histopathology images (e.g., H&E-IHC) is an emerging tool in digital pathology, enabling faster and cheaper workflows by synthesizing target stains from routinely acquired slides. Yet, the quality of virtual staining…
Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, and security constraints have posed challenges for their…
Class imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. One efficient and flexible strategy to deal with this problem is to employ sampling techniques before training a multi-label…
In 2008, melamine in infant formula forced laboratories across three continents to verify a compound they had never monitored. Non-targeted analysis using LC/GC-HRMS handles these cases. But when findings trigger regulatory action,…
As Industry 4.0 progresses, flexible manufacturing has become a cornerstone of modern industrial systems, with equipment automation playing a pivotal role. However, existing control software for industrial equipment, typically reliant on…
Modern climate projections lack adequate spatial and temporal resolution due to computational constraints, leading to inaccuracies in representing critical processes like thunderstorms that occur on the sub-resolution scale. Hybrid methods…
Acquiring accurate labels on large-scale datasets is both time consuming and expensive. To reduce the dependency of deep learning models on learning from clean labeled data, several recent research efforts are focused on learning with noisy…