English
Related papers

Related papers: Subtle Data Crimes: Naively training machine learn…

200 papers

Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and generalizability of models trained through supervised learning…

Machine Learning · Computer Science 2025-11-27 Nicholas Pellegrino , David Szczecina , Paul Fieguth

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to…

Machine Learning · Statistics 2019-10-29 Stephan Rabanser , Stephan Günnemann , Zachary C. Lipton

This paper presents a new approach to identifying and eliminating mislabeled training instances for supervised learning. The goal of this approach is to improve classification accuracies produced by learning algorithms by improving the…

Artificial Intelligence · Computer Science 2011-06-02 C. E. Brodley , M. A. Friedl

With the increase in machine learning (ML) applications in different domains, incentives for deceiving these models have reached more than ever. As data is the core backbone of ML algorithms, attackers shifted their interest toward…

Cryptography and Security · Computer Science 2023-01-04 Kshitiz Aryal , Maanak Gupta , Mahmoud Abdelsalam

Learning with limited data is one of the biggest problems of machine learning. Current approaches to this issue consist in learning general representations from huge amounts of data before fine-tuning the model on a small dataset of…

Machine Learning · Computer Science 2023-02-22 Grégoire Mialon

Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by…

Machine Learning · Computer Science 2021-09-03 Jing Lin , Ryan Luley , Kaiqi Xiong

Deep neural models have achieved state of the art performance on a wide range of problems in computer science, especially in computer vision. However, deep neural networks often require large datasets of labeled samples to generalize…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Patrick Kage , Jay C. Rothenberger , Pavlos Andreadis , Dimitrios I. Diochnos

Deep learning based semi-supervised learning (SSL) algorithms have led to promising results in recent years. However, they tend to introduce multiple tunable hyper-parameters, making them less practical in real SSL scenarios where the…

Machine Learning · Computer Science 2024-10-30 Yulin Wang , Jiayi Guo , Shiji Song , Gao Huang

In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these…

Machine Learning · Computer Science 2021-04-07 Jaya Krishna Mandivarapu , Blake Camp , Rolando Estrada

Data pruning, which aims to downsize a large training set into a small informative subset, is crucial for reducing the enormous computational costs of modern deep learning. Though large-scale data collections invariably contain annotation…

Machine Learning · Computer Science 2023-11-03 Dongmin Park , Seola Choi , Doyoung Kim , Hwanjun Song , Jae-Gil Lee

One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In practice, however, abnormal samples are often mixed in a…

Machine Learning · Computer Science 2023-02-14 Minkyung Kim , Junsik Kim , Jongmin Yu , Jun Kyun Choi

Offline reinforcement learning (RL) can be used to improve future performance by leveraging historical data. There exist many different algorithms for offline RL, and it is well recognized that these algorithms, and their hyperparameter…

Machine Learning · Computer Science 2023-01-18 Allen Nie , Yannis Flet-Berliac , Deon R. Jordan , William Steenbergen , Emma Brunskill

Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations obtained from…

Computation and Language · Computer Science 2023-09-19 Dawei Zhu , Xiaoyu Shen , Marius Mosbach , Andreas Stephan , Dietrich Klakow

In computational social science (CSS), researchers analyze documents to explain social and political phenomena. In most scenarios, CSS researchers first obtain labels for documents and then explain labels using interpretable regression…

Methodology · Statistics 2024-01-17 Naoki Egami , Musashi Hinck , Brandon M. Stewart , Hanying Wei

Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited…

Machine Learning · Computer Science 2023-12-29 Huiling Qin , Xianyuan Zhan , Yuanxun Li , Yu Zheng

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark…

Machine Learning · Computer Science 2019-05-28 Jiaxing Wang , Yin Zheng , Xiaoshuang Chen , Junzhou Huang , Jian Cheng

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Machine Learning · Computer Science 2021-08-11 Nicholas Carlini

DDoS attacks are simple, effective, and still pose a significant threat even after more than two decades. Given the recent success in machine learning, it is interesting to investigate how we can leverage deep learning to filter out…

Cryptography and Security · Computer Science 2020-12-15 Wesley Joon-Wie Tann , Jackie Tan Jin Wei , Joanna Purba , Ee-Chien Chang

Prior works have shown that semi-supervised learning algorithms can leverage unlabeled data to improve over the labeled sample complexity of supervised learning (SL) algorithms. However, existing theoretical analyses focus on regimes where…

Machine Learning · Computer Science 2023-12-01 Alexandru Ţifrea , Gizem Yüce , Amartya Sanyal , Fanny Yang

Many problems in machine learning involve bilevel optimization (BLO), including hyperparameter optimization, meta-learning, and dataset distillation. Bilevel problems consist of two nested sub-problems, called the outer and inner problems,…

Machine Learning · Computer Science 2022-12-29 Paul Vicol , Jonathan Lorraine , Fabian Pedregosa , David Duvenaud , Roger Grosse