%0 Conference Paper %1 kdml17 %A Friesen, Natalja %A Rueping., Stefan %B Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet %C Kassel, Germany %D 2010 %E Atzmüller, Martin %E Benz, Dominik %E Hotho, Andreas %E Stumme, Gerd %K analysis graph kernels lwa2010 mining workflow %T Workflow Analysis using Graph Kernels %U http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml17.pdf %X Workflow enacting systems are a popular technology in business and e-science alike to flexibly define and enact complex data processing tasks. Since the construction of a workflow for a specific task can become quite complex, efforts are currently underway to increase the re-use of workflows through the implementation of specialized workflow repositories. While existing methods to exploit the knowledge in these repositories usually consider workflows as an atomic entity, our work is based on the fact that workflows can naturally be viewed as graphs. Hence, in this paper we investigate the use of graph kernels for the problems of workflow discovery, workflow recommendation, and workflow pattern extraction, paying special attention on the typical situation of few labeled and many unlabeled workflows. To empirically demonstrate the feasibility of our approach we investigate a dataset of bioinformatics workflows retrieved from the website myexperiment.org. Note: This paper has been accepted at the Workshop on Service-Oriented Knowledge Discovery (SoKD 2010)

@inproceedings{kdml17, abstract = {Workflow enacting systems are a popular technology in business and e-science alike to flexibly define and enact complex data processing tasks. Since the construction of a workflow for a specific task can become quite complex, efforts are currently underway to increase the re-use of workflows through the implementation of specialized workflow repositories. While existing methods to exploit the knowledge in these repositories usually consider workflows as an atomic entity, our work is based on the fact that workflows can naturally be viewed as graphs. Hence, in this paper we investigate the use of graph kernels for the problems of workflow discovery, workflow recommendation, and workflow pattern extraction, paying special attention on the typical situation of few labeled and many unlabeled workflows. To empirically demonstrate the feasibility of our approach we investigate a dataset of bioinformatics workflows retrieved from the website myexperiment.org. [Note: This paper has been accepted at the Workshop on Service-Oriented Knowledge Discovery (SoKD 2010)]}, added-at = {2010-10-05T14:42:07.000+0200}, address = {Kassel, Germany}, author = {Friesen, Natalja and Rueping., Stefan}, biburl = {https://www.bibsonomy.org/bibtex/2572655b8e92bf7fa6b6db045ef8d047f/folke}, booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen {\&} Adaptivitaet}, crossref = {lwa2010}, editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, interhash = {2c7a034072faa89a74cb13f1711c3534}, intrahash = {572655b8e92bf7fa6b6db045ef8d047f}, keywords = {analysis graph kernels lwa2010 mining workflow}, presentation_end = {2010-10-05 15:00:00}, presentation_start = {2010-10-05 14:30:00}, room = {0446}, session = {joint5}, timestamp = {2010-10-05T14:42:07.000+0200}, title = {Workflow Analysis using Graph Kernels}, track = {kdml}, url = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml17.pdf}, year = 2010 }