Probabilistic Message Passing in

1

• Probabilistic Message Passing in
• Peer Data Management Systems
• Philippe Cudré-Mauroux, Karl Aberer EPFL
• Andras Feher, T.U. Darmstadt

2
Peer Data Management Systems
escDate ? xapCreateDate
weather
article

• Pairwise mappings
• Query reformulation between two peers (schemas)
• Local mappings overcome global heterogeneity
• Transitive closures on mapping operations

3
Problem Precision/Recall Tradeoff

• Semantic Query routing
• To whom shall I forward a query posed against my
  local schema?
• Some (most) mappings will be (partially) faulty
• Low expressive power of mappings
• samePropertyAs / sameClassAs
• subclassOf
• Automatic schema alignment techniques
• Different views on conceptualizations
• Local query resolution
• Low recall
• Flooding (PDMS so far)
• Low precision
• Standard deductive integration is not sufficient
• Uncertainty on mappings and conceptualizations

4
Probabilistic Message Passing

• Link-based analysis of the PDMS
• - Automatically deriving quality measures for the
  mappings
• Decentralized computations
• - Analysis of loops and parallel paths
• - Iterative sum-product computations (loopy
  belief propagation)

a priori information on mapping
5
Implemented System

• Schemas
• Import from OWL (Web Ontology Language)
• Mappings
• KnowledgeWeb Ontology Alignment API
• Import from RDF/XML
• Automated on-the-fly creation
• Comparison to standard alignments
• Automatic derivation of quality measures
  P(mcorrect F) for the mappings using
  iterative message-passing
• Reference
• Probabilistic Message-Passing in Peer-Data
  Management Systems
• Philippe Cudré-Mauroux, Karl Aberer, and Andras
  Feher
• International Conference on Data Engineering
  (ICDE 06).