Towards time-evolving analytics: Online learning for time-dependent evolving data streams-Reference-Cited by-同舟云学术

Towards time-evolving analytics: Online learning for time-dependent evolving data streams

Published:2022-12-20 Issue: Volume: Page:1-16
ISSN:2451-8492
Container-title:Data Science
language:
Short-container-title:DS

Author:

Ziffer Giacomo¹^ORCID,Bernardo Alessio¹^ORCID,Della Valle Emanuele¹^ORCID,Cerqueira Vitor²^ORCID,Bifet Albert³^ORCID

Affiliation:

1. DEIB, Politecnico di Milano, Milano, Italy

2. Dalhousie University, Halifax, Canada

3. University of Waikato, Hamilton, New Zealand

Abstract

Traditional historical data analytics is at risk in a world where volatility, uncertainty, complexity, and ambiguity are the new normal. While Streaming Machine Learning (SML) and Time-series Analytics (TSA) attack some aspects of the problem, we still need a comprehensive solution. SML trains models using fewer data and in a continuous/adaptive way relaxing the assumption that data points are identically distributed. TSA considers temporal dependence among data points, but it assumes identical distribution. Every Data Scientist fights this battle with ad-hoc solutions. In this paper, we claim that, due to the temporal dependence on the data, the existing solutions do not represent robust solutions to efficiently and automatically keep models relevant even when changes occur, and real-time processing is a must. We propose a novel and solid scientific foundation for Time-Evolving Analytics from this perspective. Such a framework aims to develop the logical, methodological, and algorithmic foundations for fast, scalable, and resilient analytics.

Publisher

IOS Press

Subject

General Medicine

Reference46 articles.

1. O. Anava, E. Hazan, S. Mannor and O. Shamir, Online learning for time series prediction, in: COLT, JMLR Workshop and Conference Proceedings, Vol. 30, JMLR.org, 2013, pp. 172–184, available at http://proceedings.mlr.press/v30/Anava13.html.

2. B. Babcock, M. Datar, R. Motwani et al., Load shedding techniques for data stream systems, in: Proceedings of the 2003 Workshop on Management and Processing of Data Streams, Vol. 577, Citeseer, 2003, available at http://www-cs-students.stanford.edu/~datar/papers/mpds03.pdf.

3. AutoML for Stream k-Nearest Neighbors Classification

4. Classifier Concept Drift Detection and the Illusion of Progress

5. Learning from Time-Changing Data with Adaptive Windowing

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series;Advances in Knowledge Discovery and Data Mining;2023