Related papers: How Low Can You Go? The Data-Light SE Challenge

To scale optimization and simulation, prior work has explored training machine-learning surrogates that map problem parameters to solutions inexpensively at inference time. Unfortunately, commonly used approaches, including supervised and…

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…

Small-scale automation services in Software Engineering, known as SE Bots, have gradually infiltrated every aspect of daily software development with the goal of enhancing productivity and well-being. While leading the OSS development,…

Many datasets and approaches in ambient sound analysis use weakly labeled data.Weak labels are employed because annotating every data sample with a strong label is too expensive.Yet, their impact on the performance in comparison to strong…

Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding…

We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning. Theoretically, we revisit the simple Gaussian model of Schmidt et al. that shows a sample complexity gap…

There is a growing need for better development methods and tools to keep up with the increasing complexity of new software systems. New types of user interfaces, the need for intelligent components, sustainability concerns, ... bring new…

In the last few years, unpaired image-to-image translation has witnessed remarkable progress. Although the latest methods are able to generate realistic images, they crucially rely on a large number of labeled images. Recently, some methods…

Large Language Models (LLMs) have demonstrated remarkable capabilities in software engineering, yet comprehensive benchmarks covering diverse SE activities remain limited. We present a multi-task evaluation of 11 state-of-the-art LLMs…

Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to…

Semi-supervised learning is a powerful technique for leveraging unlabeled data to improve machine learning models, but it can be affected by the presence of ``informative'' labels, which occur when some classes are more likely to be labeled…

To mitigate the burden of data labeling, we aim at improving data efficiency for both classification and regression setups in deep learning. However, the current focus is on classification problems while rare attention has been paid to deep…

Background: Sustainable software engineering (SSE) means creating software in a way that meets present needs without undermining our collective capacity to meet our future needs. It is typically conceptualized as several intersecting…

Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however,…

Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting data incurs unnecessary present costs, while under-collecting…

Semi-supervised datasets are ubiquitous across diverse domains where obtaining fully labeled data is costly or time-consuming. The prevalence of such datasets has consistently driven the demand for new tools and methods that exploit the…

Labeling data is an important step in the supervised machine learning lifecycle. It is a laborious human activity comprised of repeated decision making: the human labeler decides which of several potential labels to apply to each example.…

We show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT). To this end, we introduce a new baseline called Centroid Networks, a modification of…

Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the…

State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency regularization and pseudo-labeling. During pseudo-labeling,…