Towards Interactive Recommender Systems with the Doctor-in-the-Loop

Andreas Holzinger, Andre Calero-Valdez, Martina Ziefle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recommender Systems are a perfect example for automatic Machine Learning (aML) – which is the fastest growing field in computer science generally and health informatics specifically. The general goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions and decision support – which is of the central interest of health informatics. Whilst automatic approaches greatly benefit from big data with many training sets, in the health domain experts are often confronted with a small number of complex data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive Machine Learning (iML) may be of help, which can be defined as “algorithms that can interact with agents and can optimize their learning behaviour through these interactions, where the agents can also be human”. Such a human can be an expert, i.e. a medical doctor, and this “doctor-in-the-loop” can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human expert agent involved in the learning phase. Important future research aspects are in the combined use of both human intelligence and computer intelligence, in the context of hybrid multi-agent recommender systems which can also make use of the power of crowdsourcing to make use of joint decision making – which can be very helpful e.g. in the diagnosis and treatment of rare diseases

Workshop

WorkshopHuman Factors in Information Visualization and Decision Support Systems
Abbreviated titleHFDISS 2016
CountryGermany
CityAachen
Period7/09/167/09/16
Internet address

Fingerprint

Recommender systems
Health
Learning systems
Protein folding
Computer science
Computational complexity
Decision making

Keywords

  • recommender systems
  • Machine Learning
  • Decision Support
  • Health Informatics

ASJC Scopus subject areas

  • Artificial Intelligence

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Basic - Fundamental (Grundlagenforschung)

Cite this

Holzinger, A., Calero-Valdez, A., & Ziefle, M. (2016). Towards Interactive Recommender Systems with the Doctor-in-the-Loop. In B. Weyers, & A. Dittmar (Eds.), Mensch & Computer 2016 (pp. 1-9). Gesellschaft für Informatik . DOI: 10.18420/muc2016-ws11-0001

Towards Interactive Recommender Systems with the Doctor-in-the-Loop. / Holzinger, Andreas; Calero-Valdez, Andre; Ziefle, Martina.

Mensch & Computer 2016. ed. / B. Weyers; A. Dittmar. Gesellschaft für Informatik , 2016. p. 1-9.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Holzinger, A, Calero-Valdez, A & Ziefle, M 2016, Towards Interactive Recommender Systems with the Doctor-in-the-Loop. in B Weyers & A Dittmar (eds), Mensch & Computer 2016. Gesellschaft für Informatik , pp. 1-9, Human Factors in Information Visualization and Decision Support Systems, Aachen, Germany, 7/09/16. DOI: 10.18420/muc2016-ws11-0001
Holzinger A, Calero-Valdez A, Ziefle M. Towards Interactive Recommender Systems with the Doctor-in-the-Loop. In Weyers B, Dittmar A, editors, Mensch & Computer 2016. Gesellschaft für Informatik . 2016. p. 1-9. Available from, DOI: 10.18420/muc2016-ws11-0001
Holzinger, Andreas ; Calero-Valdez, Andre ; Ziefle, Martina. / Towards Interactive Recommender Systems with the Doctor-in-the-Loop. Mensch & Computer 2016. editor / B. Weyers ; A. Dittmar. Gesellschaft für Informatik , 2016. pp. 1-9
@inproceedings{dcd5f91969864e7e9e4f63eb9ced7b5a,
title = "Towards Interactive Recommender Systems with the Doctor-in-the-Loop",
abstract = "Recommender Systems are a perfect example for automatic Machine Learning (aML) – which is the fastest growing field in computer science generally and health informatics specifically. The general goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions and decision support – which is of the central interest of health informatics. Whilst automatic approaches greatly benefit from big data with many training sets, in the health domain experts are often confronted with a small number of complex data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive Machine Learning (iML) may be of help, which can be defined as “algorithms that can interact with agents and can optimize their learning behaviour through these interactions, where the agents can also be human”. Such a human can be an expert, i.e. a medical doctor, and this “doctor-in-the-loop” can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human expert agent involved in the learning phase. Important future research aspects are in the combined use of both human intelligence and computer intelligence, in the context of hybrid multi-agent recommender systems which can also make use of the power of crowdsourcing to make use of joint decision making – which can be very helpful e.g. in the diagnosis and treatment of rare diseases",
keywords = "recommender systems, Machine Learning, Decision Support, Health Informatics",
author = "Andreas Holzinger and Andre Calero-Valdez and Martina Ziefle",
year = "2016",
doi = "10.18420/muc2016-ws11-0001",
language = "English",
pages = "1--9",
editor = "B. Weyers and A. Dittmar",
booktitle = "Mensch & Computer 2016",
publisher = "Gesellschaft f{\"u}r Informatik",
address = "Germany",

}

TY - GEN

T1 - Towards Interactive Recommender Systems with the Doctor-in-the-Loop

AU - Holzinger,Andreas

AU - Calero-Valdez,Andre

AU - Ziefle,Martina

PY - 2016

Y1 - 2016

N2 - Recommender Systems are a perfect example for automatic Machine Learning (aML) – which is the fastest growing field in computer science generally and health informatics specifically. The general goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions and decision support – which is of the central interest of health informatics. Whilst automatic approaches greatly benefit from big data with many training sets, in the health domain experts are often confronted with a small number of complex data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive Machine Learning (iML) may be of help, which can be defined as “algorithms that can interact with agents and can optimize their learning behaviour through these interactions, where the agents can also be human”. Such a human can be an expert, i.e. a medical doctor, and this “doctor-in-the-loop” can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human expert agent involved in the learning phase. Important future research aspects are in the combined use of both human intelligence and computer intelligence, in the context of hybrid multi-agent recommender systems which can also make use of the power of crowdsourcing to make use of joint decision making – which can be very helpful e.g. in the diagnosis and treatment of rare diseases

AB - Recommender Systems are a perfect example for automatic Machine Learning (aML) – which is the fastest growing field in computer science generally and health informatics specifically. The general goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions and decision support – which is of the central interest of health informatics. Whilst automatic approaches greatly benefit from big data with many training sets, in the health domain experts are often confronted with a small number of complex data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive Machine Learning (iML) may be of help, which can be defined as “algorithms that can interact with agents and can optimize their learning behaviour through these interactions, where the agents can also be human”. Such a human can be an expert, i.e. a medical doctor, and this “doctor-in-the-loop” can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human expert agent involved in the learning phase. Important future research aspects are in the combined use of both human intelligence and computer intelligence, in the context of hybrid multi-agent recommender systems which can also make use of the power of crowdsourcing to make use of joint decision making – which can be very helpful e.g. in the diagnosis and treatment of rare diseases

KW - recommender systems

KW - Machine Learning

KW - Decision Support

KW - Health Informatics

UR - http://dl.mensch-und-computer.de/handle/123456789/5118?discover=true

U2 - 10.18420/muc2016-ws11-0001

DO - 10.18420/muc2016-ws11-0001

M3 - Conference contribution

SP - 1

EP - 9

BT - Mensch & Computer 2016

PB - Gesellschaft für Informatik

ER -