Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm

Marcel Gehrke; Tanya Braun; Ralf Möller

doi:10.1007/978-3-030-00111-7_4

Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm

Institute of Information Systems

Abstract

The lifted dynamic junction tree algorithm (LDJT) answers filtering and prediction queries efficiently for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. Unfortunately, a non-ideal elimination order can lead to unnecessary groundings.

Original language	English
Title of host publication	KI 2018: Advances in Artificial Intelligence
Editors	Frank Trollmann, Anni-Yasmin Turhan
Number of pages	8
Volume	11117
Place of Publication	Cham
Publisher	Springer International Publishing
Publication date	30.08.2018
Pages	38-45
ISBN (Print)	978-3-030-00110-0
ISBN (Electronic)	978-3-030-00111-7
DOIs	https://doi.org/10.1007/978-3-030-00111-7_4
Publication status	Published - 30.08.2018
Event	41st German Conference on Artificial Intelligence - Berlin, Germany Duration: 24.09.2018 → 28.09.2018 Conference number: 218679

DFG Research Classification Scheme

4.43-01 Theoretical Computer Science

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-00111-7_4

Cite this

Gehrke, M., Braun, T., & Möller, R. (2018). Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm. In F. Trollmann, & A.-Y. Turhan (Eds.), KI 2018: Advances in Artificial Intelligence (Vol. 11117, pp. 38-45). (Lecture Notes in Computer Science; Vol. 11117). Springer International Publishing. https://doi.org/10.1007/978-3-030-00111-7_4

@inproceedings{df105afe8a0b4e98be423667b4cf4102,

title = "Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm",

abstract = "The lifted dynamic junction tree algorithm (LDJT) answers filtering and prediction queries efficiently for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. Unfortunately, a non-ideal elimination order can lead to unnecessary groundings.",

author = "Marcel Gehrke and Tanya Braun and Ralf M{\"o}ller",

year = "2018",

month = aug,

day = "30",

doi = "10.1007/978-3-030-00111-7_4",

language = "English",

isbn = "978-3-030-00110-0",

volume = "11117",

series = "Lecture Notes in Computer Science",

publisher = "Springer International Publishing",

pages = "38--45",

editor = "Frank Trollmann and Anni-Yasmin Turhan",

booktitle = "KI 2018: Advances in Artificial Intelligence",

note = "41st German Conference on Artificial Intelligence<br/>, KI 2018 ; Conference date: 24-09-2018 Through 28-09-2018",

}

Gehrke, M, Braun, T & Möller, R 2018, Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm. in F Trollmann & A-Y Turhan (eds), KI 2018: Advances in Artificial Intelligence. vol. 11117, Lecture Notes in Computer Science, vol. 11117, Springer International Publishing, Cham, pp. 38-45, 41st German Conference on Artificial Intelligence
, Berlin, Berlin, Germany, 24.09.18. https://doi.org/10.1007/978-3-030-00111-7_4

Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm. / Gehrke, Marcel; Braun, Tanya; Möller, Ralf.
KI 2018: Advances in Artificial Intelligence. ed. / Frank Trollmann; Anni-Yasmin Turhan. Vol. 11117 Cham: Springer International Publishing, 2018. p. 38-45 (Lecture Notes in Computer Science; Vol. 11117).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm

AU - Gehrke, Marcel

AU - Braun, Tanya

AU - Möller, Ralf

N1 - Conference code: 218679

PY - 2018/8/30

Y1 - 2018/8/30

N2 - The lifted dynamic junction tree algorithm (LDJT) answers filtering and prediction queries efficiently for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. Unfortunately, a non-ideal elimination order can lead to unnecessary groundings.

AB - The lifted dynamic junction tree algorithm (LDJT) answers filtering and prediction queries efficiently for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. Unfortunately, a non-ideal elimination order can lead to unnecessary groundings.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85054535250&origin=inward&txGid=be91c49e9f6ec10e030022c2a524135c

U2 - 10.1007/978-3-030-00111-7_4

DO - 10.1007/978-3-030-00111-7_4

M3 - Conference contribution

SN - 978-3-030-00110-0

VL - 11117

T3 - Lecture Notes in Computer Science

SP - 38

EP - 45

BT - KI 2018: Advances in Artificial Intelligence

A2 - Trollmann, Frank

A2 - Turhan, Anni-Yasmin

PB - Springer International Publishing

CY - Cham

T2 - 41st German Conference on Artificial Intelligence<br/>

Y2 - 24 September 2018 through 28 September 2018

ER -

Towards Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm

Abstract

DFG Research Classification Scheme

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this