Related papers: Stuttgart Open Relay Degradation Dataset (SOReDD)

Deep learning models often require large amounts of data for training, leading to increased costs. It is particularly challenging in medical imaging, i.e., gathering distributed data for centralized training, and meanwhile, obtaining…

This paper presents a dataset, called Reeds, for research on robot perception algorithms. The dataset aims to provide demanding benchmark opportunities for algorithms, rather than providing an environment for testing application-specific…

In this work, we observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks (e.g., semantic segmentation). We refer to this phenomenon as Self-supervised…

Distributed data analytic engines like Spark are common choices to process massive data in industry. However, the performance of Spark SQL highly depends on the choice of configurations, where the optimal ones vary with the executed…

A coreset is a subset of the training set, using which a machine learning algorithm obtains performances similar to what it would deliver if trained over the whole original data. Coreset discovery is an active and open line of research as…

Federated learning (FL) has emerged as a promising approach to training machine learning models across decentralized data sources while preserving data privacy, particularly in manufacturing and shared production environments. However, the…

The quality of the data in a dataset can have a substantial impact on the performance of a machine learning model that is trained and/or evaluated using the dataset. Effective dataset management, including tasks such as data cleanup,…

Machine learning is traditionally studied at the model level: researchers measure and improve the accuracy, robustness, bias, efficiency, and other dimensions of specific models. In practice, the societal impact of machine learning is…

The proliferation of IoT sensors and their deployment in various industries and applications has brought about numerous analysis opportunities in this Big Data era. However, drift of those sensor measurements poses major challenges to…

Use of machine learning to perform database operations, such as indexing, cardinality estimation, and sorting, is shown to provide substantial performance benefits. However, when datasets change and data distribution shifts, empirical…

Data-driven models analyze power grids under incomplete physical information, and their accuracy has been mostly validated empirically using certain training and testing datasets. This paper explores error bounds for data-driven models…

Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable…

Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects…

Machine unlearning considers the removal of the contribution of a set of data points from a trained model. In a distributed setting, where a server orchestrates training using data available at a set of remote users, unlearning is essential…

When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an…

Machine learning-based techniques open up many opportunities and improvements to derive deeper and more practical insights from data that can help businesses make informed decisions. However, the majority of these techniques focus on the…

We consider a serious, previously-unexplored challenge facing almost all approaches to scaling up entity resolution (ER) to multiple data sources: the prohibitive cost of labeling training data for supervised learning of similarity scores…

Deep learning promises performant anomaly detection on time-variant datasets, but greatly suffers from low availability of suitable training datasets and frequently changing tasks. Deep transfer learning offers mitigation by letting…

Learning from demonstration is widely used for robot navigation, yet it suffers from a fundamental limitation: demonstrations consist predominantly of successful behaviors and provide limited coverage of unsafe states. This limitation leads…

Neural surrogates for Partial Differential Equations (PDEs) often suffer significant performance degradation when evaluated on problem configurations outside their training distribution, such as new initial conditions or structural…