English
Related papers

Related papers: DiffPrep: Differentiable Data Preprocessing Pipeli…

200 papers

In this paper, we present our vision of differentiable ML pipelines called DiffML to automate the construction of ML pipelines in an end-to-end fashion. The idea is that DiffML allows to jointly train not just the ML model itself but also…

Databases · Computer Science 2022-07-06 Benjamin Hilprecht , Christian Hammacher , Eduardo Reis , Mohamed Abdelaal , Carsten Binnig

Data preprocessing pipelines, which includes data decoding, cleaning, and transforming, are a crucial component of Machine Learning (ML) training. Thy are computationally intensive and often become a major bottleneck, due to the increasing…

Hardware Architecture · Computer Science 2024-09-24 Yu Zhu , Wenqi Jiang , Gustavo Alonso

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…

Databases · Computer Science 2026-02-10 Meihao Fan , Ju Fan , Yuxin Zhang , Shaolei Zhang , Xiaoyong Du , Jie Song , Peng Li , Fuxin Jiang , Tieying Zhang , Jianjun Chen

Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine learning applications…

Machine Learning · Computer Science 2018-10-24 Brandon Schoenfeld , Christophe Giraud-Carrier , Mason Poggemann , Jarom Christensen , Kevin Seppi

Feature preprocessing, which transforms raw input features into numerical representations, is a crucial step in automated machine learning (AutoML) systems. However, the existing systems often have a very small search space for feature…

Machine Learning · Computer Science 2023-03-01 Diego Martinez , Daochen Zha , Qiaoyu Tan , Xia Hu

Data scientists seeking a good supervised learning model on a new dataset have many choices to make: they must preprocess the data, select features, possibly reduce the dimension, select an estimation algorithm, and choose hyperparameters…

Machine Learning · Computer Science 2020-06-11 Chengrun Yang , Jicong Fan , Ziyang Wu , Madeleine Udell

Preprocessing pipelines in deep learning aim to provide sufficient data throughput to keep the training processes busy. Maximizing resource utilization is becoming more challenging as the throughput of training processes increases with…

Machine Learning · Computer Science 2022-03-28 Alexander Isenko , Ruben Mayer , Jeffrey Jedele , Hans-Arno Jacobsen

Pipeline parallelism is a crucial paradigm for large-scale model training. However, imbalances in memory footprint across stages can lead to significant GPU memory wastage, limiting the model sizes that pipeline parallelism can effectively…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-12 Xuan Peng , Xuanhua Shi , Haolin Zhang , Yunfei Zhao , Xuehai Qian

Machine learning algorithms have become increasingly prevalent in multiple domains, such as autonomous driving, healthcare, and finance. In such domains, data preparation remains a significant challenge in developing accurate models,…

Databases · Computer Science 2023-04-27 Mohamed Abdelaal , Rashmi Koparde , Harald Schoening

Tabular data plays a crucial role in various domains but often suffers from missing values, thereby curtailing its potential utility. Traditional imputation techniques frequently yield suboptimal results and impose substantial computational…

Machine Learning · Computer Science 2024-03-22 Yizhu Wen , Kai Yi , Jing Ke , Yiqing Shen

In commercial systems, a pervasive requirement for automatic data preparation (ADP) is to transfer relational data from disparate sources to targets with standardized schema specifications. Previous methods rely on labor-intensive…

Artificial Intelligence · Computer Science 2025-09-23 Congcong Ge , Yachuan Liu , Yixuan Tang , Yifan Zhu , Yaofeng Tu , Yunjun Gao

Classical machine learning models, such as linear models and tree-based models, are widely used in industry. These models are sensitive to data distribution, thus feature preprocessing, which transforms features from one distribution to…

Machine Learning · Computer Science 2026-04-16 Danrui Qi , Jinglin Peng , Yongjun He , Jiannan Wang

Automated machine learning (AutoML) aims for constructing machine learning (ML) pipelines automatically. Many studies have investigated efficient methods for algorithm selection and hyperparameter optimization. However, methods for ML…

Machine Learning · Computer Science 2021-01-27 Marc-André Zöller , Tien-Dung Nguyen , Marco F. Huber

Machines learning techniques plays a preponderant role in dealing with massive amount of data and are employed in almost every possible domain. Building a high quality machine learning model to be deployed in production is a challenging…

Machine Learning · Computer Science 2019-07-02 Alexandre Quemy

Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical…

Machine Learning · Computer Science 2024-10-25 Ivan Rubachev , Nikolay Kartashev , Yury Gorishniy , Artem Babenko

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 George Cazenavette , Antonio Torralba , Vincent Sitzmann

Table processing-including cleaning, transformation, augmentation, and matching-is a foundational yet error-prone stage in real-world data pipelines. While recent LLM-based approaches show promise for automating such tasks, they often…

Artificial Intelligence · Computer Science 2026-05-13 Wei Liu , Yang Gu , Xi Yan , Zihan Nan , Beicheng Xu , Keyao Ding , Bin Cui , Wentao Zhang

As machine learning systems become increasingly integrated into high-stakes decision-making processes, ensuring fairness in algorithmic outcomes has become a critical concern. Methods to mitigate bias typically fall into three categories:…

Machine Learning · Computer Science 2025-08-22 Brodie Oldfield , Ziqi Xu , Sevvandi Kandanaarachchi

The ability to train generative models that produce realistic, safe and useful tabular data is essential for data privacy, imputation, oversampling, explainability or simulation. However, generating tabular data is not straightforward due…

Machine Learning · Computer Science 2025-09-18 G. Charbel N. Kindji , Lina Maria Rojas-Barahona , Elisa Fromont , Tanguy Urvoy

Machine learning (ML) pipeline composition and optimisation have been studied to seek multi-stage ML models, i.e. preprocessor-inclusive, that are both valid and well-performing. These processes typically require the design and traversal of…

Machine Learning · Computer Science 2021-05-04 Tien-Dung Nguyen , David Jacob Kedziora , Katarzyna Musial , Bogdan Gabrys
‹ Prev 1 2 3 10 Next ›