TU Darmstadt / ULB / TUbiblio

Learning of Process Representations Using Recurrent Neural Networks

Seeliger, Alexander ; Luettgen, Stefan ; Nolle, Timo ; Mühlhäuser, Max
La Rosa, Marcello ; Sadiq, Shazia ; Teniente, Ernest (eds.) (2021):
Learning of Process Representations Using Recurrent Neural Networks.
In: Lecture Notes in Computer Science, 12751, In: Advanced Information Systems Engineering, pp. 109-124,
Springer International Publishing, 33rd International Conference on Advanced Information Systems Engineering (CAiSE 2021), virtual Conference, 28.06-02.07.2021, ISBN 978-3-030-79382-1,
DOI: 10.1007/978-3-030-79382-1_7,
[Conference or Workshop Item]

Abstract

In process mining, many tasks use a simplified representation of a single case to perform tasks like trace clustering, anomaly detection, or subset identification. These representations may capture the control flow of the process as well as the context a case is executed in. However, most of these representations are hand-crafted, which is very time-consuming for practical use, and the incorporation of event and case attributes as contextual factors is challenging. In this paper, we propose a neural network architecture for representation learning to automate the generation. Our network is trained in a supervised fashion to learn the most meaningful features to obtain highly dense and accurate vector representations of cases of an event log. We implemented our approach and conducted experiments in the context of trace clustering with publicly available event logs to show its applicability. The results show improvements regarding the separation of cases, and that process models discovered from identified subsets are of high quality.

Item Type: Conference or Workshop Item
Erschienen: 2021
Editors: La Rosa, Marcello ; Sadiq, Shazia ; Teniente, Ernest
Creators: Seeliger, Alexander ; Luettgen, Stefan ; Nolle, Timo ; Mühlhäuser, Max
Title: Learning of Process Representations Using Recurrent Neural Networks
Language: English
Abstract:

In process mining, many tasks use a simplified representation of a single case to perform tasks like trace clustering, anomaly detection, or subset identification. These representations may capture the control flow of the process as well as the context a case is executed in. However, most of these representations are hand-crafted, which is very time-consuming for practical use, and the incorporation of event and case attributes as contextual factors is challenging. In this paper, we propose a neural network architecture for representation learning to automate the generation. Our network is trained in a supervised fashion to learn the most meaningful features to obtain highly dense and accurate vector representations of cases of an event log. We implemented our approach and conducted experiments in the context of trace clustering with publicly available event logs to show its applicability. The results show improvements regarding the separation of cases, and that process models discovered from identified subsets are of high quality.

Title of Book: Advanced Information Systems Engineering
Series Name: Lecture Notes in Computer Science
Volume: 12751
Publisher: Springer International Publishing
ISBN: 978-3-030-79382-1
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Telecooperation
Event Title: 33rd International Conference on Advanced Information Systems Engineering (CAiSE 2021)
Event Location: virtual Conference
Event Dates: 28.06-02.07.2021
Date Deposited: 23 Jun 2021 12:29
DOI: 10.1007/978-3-030-79382-1_7
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details