Related papers: Towards Interactively Improving ML Data Preparatio…

Data preparation, especially data cleaning, is very important to ensure data quality and to improve the output of automated decision systems. Since there is no single tool that covers all steps required, a combination of tools -- namely a…

Data Scientists often use notebooks to develop Data Science (DS) pipelines, particularly since they allow to selectively execute parts of the pipeline. However, notebooks for DS have many well-known flaws. We focus on the following ones in…

Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…

Over the past decade, data science and machine learning has grown from a mysterious art form to a staple tool across a variety of fields in academia, business, and government. In this paper, we introduce the concept of tree-based pipeline…

Observations made in continuous time are often irregular and contain the missing values across different channels. One approach to handle the missing data is imputing it using splines, by fitting the piecewise polynomials to the observed…

With the ever-increasing adoption of machine learning for data analytics, maintaining a machine learning pipeline is becoming more complex as both the datasets and trained models evolve with time. In a collaborative environment, the changes…

Successful data-driven science requires complex data engineering pipelines to clean, transform, and alter data in preparation for machine learning, and robust results can only be achieved when each step in the pipeline can be justified, and…

Machine learning (ML) has become a vital part in many aspects of our daily life. However, building well performing machine learning applications requires highly specialized data scientists and domain experts. Automated machine learning…

Data science has the potential to improve business in a variety of verticals. While the lion's share of data science projects uses a predictive approach, to drive improvements these predictions should become decisions. However, such a…

In recent years, large pre-trained Language Models of Code (CodeLMs) have shown promising results on various software engineering tasks. One such task is automatic code update recommendation, which transforms outdated code snippets into…

Effective issue resolution is crucial for maintaining software quality. Yet developers frequently encounter challenges such as low-quality issue reports, limited understanding of real-world workflows, and a lack of automated support. This…

Deep supervision, or known as 'intermediate supervision' or 'auxiliary supervision', is to add supervision at hidden layers of a neural network. This technique has been increasingly applied in deep neural network learning systems for…

Data preparation, which aims to transform heterogeneous and noisy raw tables into analysis-ready data, remains a major bottleneck in data science. Recent approaches leverage large language models (LLMs) to automate data preparation from…

The extent to which decoder-only language models (LMs) engage in planning, that is, organizing intermediate computations to support coherent long-range generation, remains an important question, with implications for interpretability,…

Machine learning can provide deep insights into data, allowing machines to make high-quality predictions and having been widely used in real-world applications, such as text mining, visual classification, and recommender systems. However,…

Computational models of human language often involve combinatorial problems. For instance, a probabilistic parser may marginalize over exponentially many trees to make predictions. Algorithms for such problems often employ dynamic…

The optimization of nuclear engineering designs, such as nuclear fuel assembly configurations, involves managing competing objectives like reactivity control and power distribution. This study explores the use of Optimization by Prompting,…

This research builds on work in anticipatory human-machine interaction, a subfield of human-machine interaction where machines can facilitate advantageous interactions by anticipating a user's future state. The aim of this research is to…

The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipelines are typically implemented using hard-coded "prompt…

Machine learning (ML) is believed to be an effective and efficient tool to build reliable prediction model or extract useful structure from an avalanche of data. However, ML is also criticized by its difficulty in interpretation and…