A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning

Cedric Kulbach; Lucas Cazzonelli; Hoang Anh Ngo; Minh Huong Le-Nguyen; Albert Bifet

doi:10.1007/978-3-031-74630-7_25

A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning

Cedric Kulbach
, Lucas Cazzonelli
, Hoang Anh Ngo
, Minh Huong Le-Nguyen
, Albert Bifet

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Machine learning algorithms have become indispensable in today’s world. They support and accelerate the way we make decisions based on the data at hand. This acceleration means that data structures that were valid at one moment could no longer be valid in the future. With these changing data structures, it is necessary to adapt machine learning (ML) systems incrementally to the new data. This is done with the use of online learning or continuous ML technologies. While deep learning technologies have shown exceptional performance on predefined datasets, they have not been widely applied to online, streaming, and continuous learning. In this retrospective of our tutorial titled Opportunities and Challenges of Online Deep Learning held at ECML PKDD 2023, we provide a brief overview of the opportunities but also the potential pitfalls for the application of neural networks in online learning environments using the frameworks River and Deep-River.

Original language	English
Title of host publication	Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers
Editors	Rosa Meo, Fabrizio Silvestri
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	359-372
Number of pages	14
ISBN (Print)	9783031746291
DOIs	https://doi.org/10.1007/978-3-031-74630-7_25
Publication status	Published - 1 Jan 2025
Event	23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023 - Turin, Italy Duration: 18 Sept 2023 → 22 Sept 2023

Publication series

Name	Communications in Computer and Information Science
Volume	2133 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023
Country/Territory	Italy
City	Turin
Period	18/09/23 → 22/09/23

Keywords

Concept Drift
Decision Support
Deep Learning
Neural Networks
Online Learning
Stream Learning

Access to Document

10.1007/978-3-031-74630-7_25

Cite this

Kulbach, C., Cazzonelli, L., Ngo, H. A., Le-Nguyen, M. H., & Bifet, A. (2025). A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning. In R. Meo, & F. Silvestri (Eds.), Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers (pp. 359-372). (Communications in Computer and Information Science; Vol. 2133 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-74630-7_25

Kulbach, Cedric ; Cazzonelli, Lucas ; Ngo, Hoang Anh et al. / A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning. Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. editor / Rosa Meo ; Fabrizio Silvestri. Springer Science and Business Media Deutschland GmbH, 2025. pp. 359-372 (Communications in Computer and Information Science).

@inproceedings{a922300e31344296a0feebbb445f30df,

title = "A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning",

abstract = "Machine learning algorithms have become indispensable in today{\textquoteright}s world. They support and accelerate the way we make decisions based on the data at hand. This acceleration means that data structures that were valid at one moment could no longer be valid in the future. With these changing data structures, it is necessary to adapt machine learning (ML) systems incrementally to the new data. This is done with the use of online learning or continuous ML technologies. While deep learning technologies have shown exceptional performance on predefined datasets, they have not been widely applied to online, streaming, and continuous learning. In this retrospective of our tutorial titled Opportunities and Challenges of Online Deep Learning held at ECML PKDD 2023, we provide a brief overview of the opportunities but also the potential pitfalls for the application of neural networks in online learning environments using the frameworks River and Deep-River.",

keywords = "Concept Drift, Decision Support, Deep Learning, Neural Networks, Online Learning, Stream Learning",

author = "Cedric Kulbach and Lucas Cazzonelli and Ngo, \{Hoang Anh\} and Le-Nguyen, \{Minh Huong\} and Albert Bifet",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023 ; Conference date: 18-09-2023 Through 22-09-2023",

year = "2025",

month = jan,

day = "1",

doi = "10.1007/978-3-031-74630-7\_25",

language = "English",

isbn = "9783031746291",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "359--372",

editor = "Rosa Meo and Fabrizio Silvestri",

booktitle = "Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers",

}

Kulbach, C, Cazzonelli, L, Ngo, HA, Le-Nguyen, MH & Bifet, A 2025, A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning. in R Meo & F Silvestri (eds), Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. Communications in Computer and Information Science, vol. 2133 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 359-372, 23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023, Turin, Italy, 18/09/23. https://doi.org/10.1007/978-3-031-74630-7_25

A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning. / Kulbach, Cedric; Cazzonelli, Lucas; Ngo, Hoang Anh et al.
Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. ed. / Rosa Meo; Fabrizio Silvestri. Springer Science and Business Media Deutschland GmbH, 2025. p. 359-372 (Communications in Computer and Information Science; Vol. 2133 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning

AU - Kulbach, Cedric

AU - Cazzonelli, Lucas

AU - Ngo, Hoang Anh

AU - Le-Nguyen, Minh Huong

AU - Bifet, Albert

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025/1/1

Y1 - 2025/1/1

N2 - Machine learning algorithms have become indispensable in today’s world. They support and accelerate the way we make decisions based on the data at hand. This acceleration means that data structures that were valid at one moment could no longer be valid in the future. With these changing data structures, it is necessary to adapt machine learning (ML) systems incrementally to the new data. This is done with the use of online learning or continuous ML technologies. While deep learning technologies have shown exceptional performance on predefined datasets, they have not been widely applied to online, streaming, and continuous learning. In this retrospective of our tutorial titled Opportunities and Challenges of Online Deep Learning held at ECML PKDD 2023, we provide a brief overview of the opportunities but also the potential pitfalls for the application of neural networks in online learning environments using the frameworks River and Deep-River.

AB - Machine learning algorithms have become indispensable in today’s world. They support and accelerate the way we make decisions based on the data at hand. This acceleration means that data structures that were valid at one moment could no longer be valid in the future. With these changing data structures, it is necessary to adapt machine learning (ML) systems incrementally to the new data. This is done with the use of online learning or continuous ML technologies. While deep learning technologies have shown exceptional performance on predefined datasets, they have not been widely applied to online, streaming, and continuous learning. In this retrospective of our tutorial titled Opportunities and Challenges of Online Deep Learning held at ECML PKDD 2023, we provide a brief overview of the opportunities but also the potential pitfalls for the application of neural networks in online learning environments using the frameworks River and Deep-River.

KW - Concept Drift

KW - Decision Support

KW - Deep Learning

KW - Neural Networks

KW - Online Learning

KW - Stream Learning

UR - https://www.scopus.com/pages/publications/85219203475

U2 - 10.1007/978-3-031-74630-7_25

DO - 10.1007/978-3-031-74630-7_25

M3 - Conference contribution

AN - SCOPUS:85219203475

SN - 9783031746291

T3 - Communications in Computer and Information Science

SP - 359

EP - 372

BT - Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers

A2 - Meo, Rosa

A2 - Silvestri, Fabrizio

PB - Springer Science and Business Media Deutschland GmbH

T2 - 23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023

Y2 - 18 September 2023 through 22 September 2023

ER -

Kulbach C, Cazzonelli L, Ngo HA, Le-Nguyen MH, Bifet A. A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning. In Meo R, Silvestri F, editors, Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2025. p. 359-372. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-74630-7_25