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. We extend LDJT to answer conjunctive queries over multiple time steps by avoiding eliminations, while keeping the complexity to answer a conjunctive query low. The extended version of saves computations compared to an existing approach to answer multiple lifted conjunctive queries.
Original language | English |
---|---|
Title of host publication | AI 2018: Advances in Artificial Intelligence |
Editors | Tanja Mitrovic, Bing Xue, Xiaodong Li |
Number of pages | 13 |
Volume | 11320 |
Place of Publication | Cham |
Publisher | Springer International Publishing |
Publication date | 10.11.2018 |
Pages | 543-555 |
ISBN (Print) | 978-3-030-03990-5 |
ISBN (Electronic) | 978-3-030-03991-2 |
DOIs | |
Publication status | Published - 10.11.2018 |
Event | 31st Australasian Joint Conference on Artificial Intelligence - Wellington, Niger Duration: 11.12.2018 → 14.12.2018 https://ecs.victoria.ac.nz/Events/AI2018/WebHome#gallery |
Research Areas and Centers
- Centers: Center for Artificial Intelligence Luebeck (ZKIL)
- Research Area: Intelligent Systems
DFG Research Classification Scheme
- 4.43-01 Theoretical Computer Science