Malmö University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Interactive Online Machine Learning
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0002-3155-8408
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

With the Internet of Things paradigm, the data generated by the rapidly increasing number of connected devices lead to new possibilities, such as using machine learning for activity recognition in smart environments. However, it also introduces several challenges. The sensors of different devices might be mobile and of different types, i.e. there is a need to handle streaming data from a dynamic and heterogeneous set of sensors. In machine learning, the performance is often linked to the availability and quality of annotated data. Annotating data is in general costly, but it can be even more challenging if there is not any, or a very small amount of, annotated data to train the model on at the start of learning. To handle these issues, we implement interactive and adaptive systems. By including human-in-the-loop, which we refer to as interactive machine learning, the input from users can be utilized to build the model. The type of input used in interactive machine learning is typically annotations of the data, i.e. correctly labelled data points. Generally, it is assumed that the user always provides correct labels in accordance with the chosen interactive learning strategy. In many real-world applications these assumptions are not realistic however, as users might provide incorrect labels or not provide labels at all in line with the chosen strategy.

In this thesis we explore which interactive learning strategy types are possible in the given scenario and how they affect performance, as well as the effect of machine learning algorithms on the performance. We also study how a user who is not always reliable, i.e. who does not always provide a correct label when expected to, can affect performance. We propose a taxonomy of interactive online machine learning strategies and test how the different strategies affect performance through experiments on multiple datasets. Simulated experiments are compared to experiments with human participants, to verify the results. The findings show that the overall best performing interactive learning strategy is one where the user provides labels when current estimations are incorrect, but that the best performing machine learning algorithm depends on the problem scenario. The experiments also show that a decreased reliability of the user leads to decreased performance, especially when there is a limited amount of labelled data. The robustness of the machine learning algorithms differs, where e.g. Naïve Bayes classifier is better at handling a lower reliability of the user. We also present a systematic literature review on machine teaching, a subfield of interactive machine learning where the human is proactive in the interaction. The study shows that the area of machine teaching is rapidly evolving with an increased number of publications in recent years. However, as it is still maturing, there exists several open challenges that would benefit from further exploration, e.g. how human factors can affect performance.

Place, publisher, year, edition, pages
Malmö: Malmö universitet, 2022. , p. 209
Series
Studies in Computer Science ; 18
Keywords [en]
Interactive Machine Learning, Active Learning, Machine Teaching, Online Learning
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mau:diva-51987DOI: 10.24834/isbn.9789178772810ISBN: 978-91-7877-280-3 (print)ISBN: 978-91-7877-281-0 (electronic)OAI: oai:DiVA.org:mau-51987DiVA, id: diva2:1663671
Public defence
2022-06-23, HS aula samt livestramas, Jan Waldenströms gata 25, Malmö, 10:00 (English)
Opponent
Supervisors
Note

In reference to IEEE copyrighted material which is used with permission in this thesis, the IEEE does not endorse any of Malmö University's products or services. Internal or personal use of this material is permitted.

Paper VI and VII appear in dissertation as manuscripts.

Available from: 2022-06-03 Created: 2022-06-02 Last updated: 2023-09-05Bibliographically approved
List of papers
1. Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors
Open this publication in new window or tab >>Collaborative Sensing with Interactive Learning using Dynamic Intelligent Virtual Sensors
2019 (English)In: Sensors, E-ISSN 1424-8220, Vol. 19, no 3, article id 477Article in journal (Refereed) Published
Abstract [en]

Although the availability of sensor data is becoming prevalent across many domains, it still remains a challenge to make sense of the sensor data in an efficient and effective manner in order to provide users with relevant services. The concept of virtual sensors provides a step towards this goal, however they are often used to denote homogeneous types of data, generally retrieved from a predetermined group of sensors. The DIVS (Dynamic Intelligent Virtual Sensors) concept was introduced in previous work to extend and generalize the notion of a virtual sensor to a dynamic setting with heterogenous sensors. This paper introduces a refined version of the DIVS concept by integrating an interactive machine learning mechanism, which enables the system to take input from both the user and the physical world. The paper empirically validates some of the properties of the DIVS concept. In particular, we are concerned with the distribution of different budget allocations for labelled data, as well as proactive labelling user strategies. We report on results suggesting that a relatively good accuracy can be achieved despite a limited budget in an environment with dynamic sensor availability, while proactive labeling ensures further improvements in performance.

Place, publisher, year, edition, pages
MDPI, 2019
Keywords
virtual sensors, sensor fusion, machine learning, dynamic environments, Internet of Things
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mau:diva-2628 (URN)10.3390/s19030477 (DOI)000459941200040 ()30682809 (PubMedID)2-s2.0-85060551967 (Scopus ID)30112 (Local ID)30112 (Archive number)30112 (OAI)
Available from: 2020-02-27 Created: 2020-02-27 Last updated: 2024-02-05Bibliographically approved
2. Activity Recognition through Interactive Machine Learning in a Dynamic Sensor Setting
Open this publication in new window or tab >>Activity Recognition through Interactive Machine Learning in a Dynamic Sensor Setting
2024 (English)In: Personal and Ubiquitous Computing, ISSN 1617-4909, E-ISSN 1617-4917, Vol. 28, no 1, p. 273-286Article in journal (Refereed) Published
Abstract [en]

The advances in Internet of things lead to an increased number of devices generating and streaming data. These devices can be useful data sources for activity recognition by using machine learning. However, the set of available sensors may vary over time, e.g. due to mobility of the sensors and technical failures. Since the machine learning model uses the data streams from the sensors as input, it must be able to handle a varying number of input variables, i.e. that the feature space might change over time. Moreover, the labelled data necessary for the training is often costly to acquire. In active learning, the model is given a budget for requesting labels from an oracle, and aims to maximize accuracy by careful selection of what data instances to label. It is generally assumed that the role of the oracle only is to respond to queries and that it will always do so. In many real-world scenarios however, the oracle is a human user and the assumptions are simplifications that might not give a proper depiction of the setting. In this work we investigate different interactive machine learning strategies, out of which active learning is one, which explore the effects of an oracle that can be more proactive and factors that might influence a user to provide or withhold labels. We implement five interactive machine learning strategies as well as hybrid versions of them and evaluate them on two datasets. The results show that a more proactive user can improve the performance, especially when the user is influenced by the accuracy of earlier predictions. The experiments also highlight challenges related to evaluating performance when the set of classes is changing over time.

Place, publisher, year, edition, pages
Springer, 2024
Keywords
machine learning, interactive machine learning, active learning, machine teaching, online learning, sensor data
National Category
Other Computer and Information Science Computer Sciences
Identifiers
urn:nbn:se:mau:diva-17434 (URN)10.1007/s00779-020-01414-2 (DOI)000538990600002 ()2-s2.0-85086152913 (Scopus ID)
Note

Correction available: https://doi.org/10.1007/s00779-020-01465-5

Available from: 2020-06-07 Created: 2020-06-07 Last updated: 2024-09-17Bibliographically approved
3. A Taxonomy of Interactive Online Machine Learning Strategies
Open this publication in new window or tab >>A Taxonomy of Interactive Online Machine Learning Strategies
2021 (English)In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2020, Ghent, Belgium, September 14-18, 2020, Proceedings, Part II / [ed] Hutter F.; Kersting K.; Lijffijt J.; Valera I., Springer, 2021, p. 137-153Conference paper, Published paper (Refereed)
Abstract [en]

In interactive machine learning, human users and learning algorithms work together in order to solve challenging learning problems, e.g. with limited or no annotated data or trust issues. As annotating data can be costly, it is important to minimize the amount of annotated data needed for training while still getting a high classification accuracy. This is done by attempting to select the most informative data instances for training, where the amount of instances is limited by a labelling budget. In an online learning setting, the decision of whether or not to select an instance for labelling has to be done on-the-fly, as the data arrives in a sequential order and is only valid for a limited time period. We present a taxonomy of interactive online machine learning strategies. An interactive learning strategy determines which instances to label in an unlabelled dataset. In the taxonomy we differentiate between interactive learning strategies when the computer controls the learning process (active learning) and those when human users control the learning process (machine teaching). We then make a distinction between what triggers the learning: active learning could be triggered by uncertainty, time, or randomly, whereas machine teaching could be triggered by errors, state changes, time, or factors related to the user. We also illustrate the taxonomy by implementing versions of the different strategies and performing experiments on a benchmark dataset as well as on a synthetically generated dataset. The results show that the choice of interactive learning strategy affects performance, especially in the beginning of the online learning process, when there is a limited amount of labelled data.

Place, publisher, year, edition, pages
Springer, 2021
Series
Lecture notes in computer science, ISSN 0302-9743, E-ISSN 1611-3349 ; 12458
Keywords
interactive machine learning, active learning, machine teaching, online learning, streaming data
National Category
Other Computer and Information Science
Identifiers
urn:nbn:se:mau:diva-17435 (URN)10.1007/978-3-030-67661-2_9 (DOI)000717542900009 ()2-s2.0-85103280211 (Scopus ID)978-3-030-67660-5 (ISBN)978-3-030-67661-2 (ISBN)
Conference
European Conference, ECML PKDD 2020, Ghent, Belgium, September 14-18, 2020
Available from: 2020-06-08 Created: 2020-06-08 Last updated: 2024-11-19Bibliographically approved
4. The Effects of Reluctant and Fallible Users in Interactive Online Machine Learning
Open this publication in new window or tab >>The Effects of Reluctant and Fallible Users in Interactive Online Machine Learning
2020 (English)In: Proceedings of the Workshop on Interactive Adaptive Learning co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2020) / [ed] Daniel Kottke, Georg Krempl, Vincent Lemaire, Andreas Holzinger & Adrian Calma, CEUR Workshops , 2020, p. 55-71Conference paper, Published paper (Refereed)
Abstract [en]

In interactive machine learning it is important to select the most informative data instances to label in order to minimize the effort of the human user. There are basically two categories of interactive machine learning. In the first category, active learning, it is the computational learner that selects which data to be labelled by the human user, whereas in the second one, machine teaching, the selection is done by the human teacher. It is often assumed that the human user is a perfect oracle, i.e., a label will always be provided in accordance with the interactive learning strategy and that this label will always be correct. In real-world scenarios however, these assumptions typically do not hold. In this work, we investigate how the reliability of the user providing labels affects the performance of online machine learning. Specifically, we study reluctance, i.e., to what extent the user does not provide labels in accordance with the strategy, and fallibility, i.e., to what extent the provided labels are incorrect. We show results of experiments on a benchmark dataset as well as a synthetically created dataset. By varying the degree of reluctance and fallibility of the user, the robustness of the different interactive learning strategies and machine learning algorithms is explored. The experiments show that there is a varying robustness of the strategies and algorithms. Moreover, certain machine learning algorithms are more robust towards reluctance compared to fallibility, while the opposite is true for others

Place, publisher, year, edition, pages
CEUR Workshops, 2020
Series
CEUR Workshop Proceedings, E-ISSN 1613-0073
National Category
Software Engineering
Identifiers
urn:nbn:se:mau:diva-17673 (URN)2-s2.0-85091963929 (Scopus ID)
Conference
Interactive Adaptive Learning 2020, Ghent, Belgium, September 14th, 2020.
Available from: 2020-07-03 Created: 2020-07-03 Last updated: 2024-12-04Bibliographically approved
5. Active Learning and Machine Teaching for Online Learning: A Study of Attention and Labelling Cost
Open this publication in new window or tab >>Active Learning and Machine Teaching for Online Learning: A Study of Attention and Labelling Cost
2021 (English)In: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Institute of Electrical and Electronics Engineers (IEEE), 2021Conference paper, Published paper (Refereed)
Abstract [en]

Interactive Machine Learning (ML) has the potential to lower the manual labelling effort needed, as well as increase classification performance by incorporating a human-in-the loop component. However, the assumptions made regarding the interactive behaviour of the human in experiments are often not realistic. Active learning typically treats the human as a passive, but always correct, participant. Machine teaching provides a more proactive role for the human, but generally assumes that the human is constantly monitoring the learning process. In this paper, we present an interactive online framework and perform experiments to compare active learning, machine teaching and combined approaches. We study not only the classification performance, but also the effort (to label samples) and attention (to monitor the ML system) required of the human. Results from experiments show that a combined approach generally performs better with less effort compared to active learning and machine teaching. With regards to attention, the best performing strategy varied depending on the problem setup.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2021
National Category
Computer Sciences
Identifiers
urn:nbn:se:mau:diva-51515 (URN)10.1109/icmla52953.2021.00197 (DOI)000779208200189 ()2-s2.0-85125866078 (Scopus ID)978-1-6654-4337-1 (ISBN)978-1-6654-4338-8 (ISBN)
Conference
2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Pasadena, CA, USA, 13-16 Dec. 2021
Funder
Knowledge Foundation
Available from: 2022-05-18 Created: 2022-05-18 Last updated: 2023-09-05Bibliographically approved
6. Machine Teaching: A Systematic Literature Review
Open this publication in new window or tab >>Machine Teaching: A Systematic Literature Review
2022 (English)Manuscript (preprint) (Other academic)
National Category
Computer Sciences
Identifiers
urn:nbn:se:mau:diva-52023 (URN)
Available from: 2022-06-03 Created: 2022-06-03 Last updated: 2024-01-16Bibliographically approved
7. Human Factors in Interactive Online Machine Learning
Open this publication in new window or tab >>Human Factors in Interactive Online Machine Learning
2023 (English)In: HHAI 2023: Augmenting Human Intellect / [ed] Paul Lukowicz; Sven Mayer; Janin Koch; John Shawe-Taylor; Ilaria Tiddi, IOS Press, 2023, p. 33-45Conference paper, Published paper (Refereed)
Abstract [en]

Interactive machine learning (ML) adds a human-in-the-loop aspect to a ML system. Even though the input from human users to the system is a central part of the concept, the uncertainty caused by the human feedback is often not considered in interactive ML. The assumption that the human user is expected to always provide correct feedback, typically does not hold in real-world scenarios. This is especially important for when the cognitive workload of the human is high, for instance in online learning from streaming data where there are time constraints for providing the feedback. We present experiments of interactive online ML with human participants, and compare the results to simulated experiments where humans are always correct. We found combining the two interactive learning paradigms, active learning and machine teaching, resulted in better performance compared to machine teaching alone. The results also showed an increased discrepancy between the experiments with human participants and the simulated experiments when the cognitive workload was increased. The findings suggest the importance of taking uncertainty caused by human factors into consideration in interactive ML, especially in situations which requires a high cognitive workload for the human.

Place, publisher, year, edition, pages
IOS Press, 2023
Series
Frontiers in Artificial Intelligence and Application, ISSN 0922-6389, E-ISSN 1879-8314 ; 368
Keywords
interactive machine learning, online learning, human factors
National Category
Computer Sciences
Identifiers
urn:nbn:se:mau:diva-61687 (URN)10.3233/faia230073 (DOI)001150361600003 ()2-s2.0-85171485242 (Scopus ID)978-1-64368-394-2 (ISBN)978-1-64368-395-9 (ISBN)
Conference
HHAI 2023, the 2nd International Conference on Hybrid Human-Artificial Intelligence, 26-30 June 2023, Munich, Germany
Available from: 2023-07-06 Created: 2023-07-06 Last updated: 2024-02-26Bibliographically approved

Open Access in DiVA

fulltext(6476 kB)642 downloads
File information
File name FULLTEXT02.pdfFile size 6476 kBChecksum SHA-512
d82a77f51f178544c659ef5b44c0b45a673c797f89e7e67fbd1500409dc71425f5a5bb19ab72a1005a6275bf364e61c91bea869bc4e5316d6b8884258a2f285b
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Authority records

Tegen, Agnes

Search in DiVA

By author/editor
Tegen, Agnes
By organisation
Department of Computer Science and Media Technology (DVMT)Internet of Things and People (IOTAP)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 642 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 1430 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf