English
Related papers

Related papers: Finding Order in Chaos: A Novel Data Augmentation …

200 papers

In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series…

Machine Learning · Computer Science 2021-09-15 Brian Kenji Iwana , Seiichi Uchida

Predicting chaotic dynamical systems is critical in many scientific fields, such as weather forecasting, but challenging due to the characteristic sensitive dependence on initial conditions. Traditional modeling approaches require extensive…

Machine Learning · Computer Science 2025-03-12 Christof Schötz , Alistair White , Maximilian Gelbrecht , Niklas Boers

Data augmentation is a technique to improve the generalization ability of machine learning methods by increasing the size of the dataset. However, since every augmentation method is not equally effective for every dataset, you need to…

Machine Learning · Computer Science 2022-05-31 Daisuke Oba , Shinnosuke Matsuo , Brian Kenji Iwana

Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even…

Information Retrieval · Computer Science 2023-11-28 Abhijit Anand , Jurek Leonhardt , Jaspreet Singh , Koustav Rudra , Avishek Anand

Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augmentation methods have led to further improvements on image…

Machine Learning · Computer Science 2021-02-17 Elizabeth Fons , Paula Dawson , Xiao-jun Zeng , John Keane , Alexandros Iosifidis

Detection of periodic patterns of interest within noisy time series data plays a critical role in various tasks, spanning from health monitoring to behavior analysis. Existing learning techniques often rely on labels or clean versions of…

Machine Learning · Computer Science 2025-06-24 Berken Utku Demirel , Christian Holz

Machine learning has gained widespread attention as a powerful tool to identify structure in complex, high-dimensional data. However, these techniques are ostensibly inapplicable for experimental systems where data is scarce or expensive to…

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on…

Information Retrieval · Computer Science 2023-10-25 Yang Yu , Qi Liu , Kai Zhang , Yuren Zhang , Chao Song , Min Hou , Yuqing Yuan , Zhihao Ye , Zaixi Zhang , Sanshi Lei Yu

Large-scale classification of data where classes are structurally organized in a hierarchy is an important area of research. Top-down approaches that exploit the hierarchy during the learning and prediction phase are efficient for large…

Machine Learning · Computer Science 2017-06-06 Azad Naik , Huzefa Rangwala

We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are treated as vectors that are first lifted into a higher-dimensional space and then used as…

Machine Learning · Computer Science 2026-04-21 Panos Stinis

We develop a novel data-driven nonlinear mixup mechanism for graph data augmentation and present different mixup functions for sample pairs and their labels. Mixup is a data augmentation method to create new training data by linearly…

Machine Learning · Computer Science 2022-10-31 Madeline Navarro , Santiago Segarra

Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views of unlabeled samples and then learns effective…

Machine Learning · Computer Science 2024-01-11 Yucheng Wang , Yuecong Xu , Jianfei Yang , Min Wu , Xiaoli Li , Lihua Xie , Zhenghua Chen

Time-series data augmentation mitigates the issue of insufficient training data for deep learning models. Yet, existing augmentation methods are mainly designed for classification, where class labels can be preserved even if augmentation…

Machine Learning · Computer Science 2023-03-28 Xiyuan Zhang , Ranak Roy Chowdhury , Jingbo Shang , Rajesh Gupta , Dezhi Hong

Data augmentation is widely used for training a neural network given little labeled data. A common practice of augmentation training is applying a composition of multiple transformations sequentially to the data. Existing augmentation…

Machine Learning · Computer Science 2024-08-27 Dongyue Li , Kailai Chen , Predrag Radivojac , Hongyang R. Zhang

Real-world time series data that commonly reflect sequential human behavior are often uniquely irregularly sampled and sparse, with highly nonuniform sampling over time and entities. Yet, commonly-used pretraining and augmentation methods…

Machine Learning · Computer Science 2023-08-29 Nicasia Beebe-Wang , Sayna Ebrahimi , Jinsung Yoon , Sercan O. Arik , Tomas Pfister

Time series analysis has gained significant attention due to its critical applications in diverse fields such as healthcare, finance, and sensor networks. The complexity and non-stationarity of time series make it challenging to capture the…

Machine Learning · Computer Science 2024-10-31 Guancen Lin , Cong Shen , Aijing Lin

Our study investigates the impact of data augmentation on the performance of multivariate time series models, focusing on datasets from the UCR archive. Despite the limited size of these datasets, we achieved classification accuracy…

Machine Learning · Computer Science 2024-06-11 Romain Ilbert , Thai V. Hoang , Zonghua Zhang

Sequential recommendation addresses the issue of preference drift by predicting the next item based on the user's previous behaviors. Recently, a promising approach using contrastive learning has emerged, demonstrating its effectiveness in…

Information Retrieval · Computer Science 2023-08-08 Dongjun Lee , Donggeun Ko , Jaekwang Kim

The increased availability of medical data has significantly impacted healthcare by enabling the application of machine / deep learning approaches in various instances. However, medical datasets are usually small and scattered across…

Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization…

Machine Learning · Computer Science 2023-10-17 Yingtian Zou , Vikas Verma , Sarthak Mittal , Wai Hoh Tang , Hieu Pham , Juho Kannala , Yoshua Bengio , Arno Solin , Kenji Kawaguchi