Related papers: Training from Zero: Radio Frequency Machine Learni…

Machine Learning (ML) has been integrated into various software and systems. Two main components are essential for training an ML model: the training data and the ML algorithm. Given the critical role of data in ML system development, it…

Data is fundamental to the training of language models (LM). Recent research has been dedicated to data efficiency, which aims to maximize performance by selecting a minimal or optimal subset of training data. Techniques such as data…

Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers that are performatively stable, i.e. optimal for the data distribution they induce. Standard…

Modern software systems are built to be used in dynamic environments using configuration capabilities to adapt to changes and external uncertainties. In a self-adaptation context, we are often interested in reasoning about the performance…

Machine learning (ML) models often require large amounts of data to perform well. When the available data is limited, model trainers may need to acquire more data from external sources. Often, useful data is held by private entities who are…

We identify the task of measuring data to quantitatively characterize the composition of machine learning data and datasets. Similar to an object's height, width, and volume, data measurements quantify different attributes of data along…

In the Machine Learning (ML) model development lifecycle, training candidate models using an offline holdout dataset and identifying the best model for the given task is only the first step. After the deployment of the selected model,…

Robust optimization (RO) is a common approach to tractably obtain safeguarding solutions for optimization problems with uncertain constraints. In this paper, we study a statistical framework to integrate data into RO, based on learning a…

Transfer learning (TL) techniques, which leverage prior knowledge gained from data with different distributions to achieve higher performance and reduced training time, are often used in computer vision (CV) and natural language processing…

The crafting of machine learning (ML) based systems requires statistical control throughout its life cycle. Careful quantification of business requirements and identification of key factors that impact the business requirements reduces the…

Even though deep neural models have achieved superhuman performance on many popular benchmarks, they have failed to generalize to OOD or adversarial datasets. Conventional approaches aimed at increasing robustness include developing…

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…

The reliability of machine learning (ML) software systems is heavily influenced by changes in data over time. For that reason, ML systems require regular maintenance, typically based on model retraining. However, retraining requires…

The transfer learning paradigm of model pre-training and subsequent fine-tuning produces high-accuracy models. While most studies recommend scaling the pre-training size to benefit most from transfer learning, a question remains: what data…

Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To…

An oft-cited challenge of federated learning is the presence of heterogeneity. \emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \emph{System heterogeneity} refers to…

Real-world data is often incomplete and contains missing values. To train accurate models over real-world datasets, users need to spend a substantial amount of time and resources imputing and finding proper values for missing data items. In…

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry. Their data curation poses the challenges of expensive human labeling, inadequate computing resources and larger experiment turn around…

The goal of machine learning is to provide solutions which are trained by data or by experience coming from the environment. Many training algorithms exist and some brilliant successes were achieved. But even in structured environments for…