1 / 10

Case-Based Solution Diversity

Case-Based Solution Diversity. Alexandra Coman H é ctor Muñoz-Avila Dept. of Computer Science & Engineering Lehigh University. Sources: cbrwiki.fdi.ucm.es/ www.iiia.csic.es/People/enric/AICom.html www.cse.lehigh.edu/~munoz/CSE335/ www.aic.nrl.navy.mil/~aha/slides/

emery
Download Presentation

Case-Based Solution Diversity

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Case-Based Solution Diversity Alexandra Coman HéctorMuñoz-Avila Dept. of Computer Science & Engineering Lehigh University • Sources: • cbrwiki.fdi.ucm.es/ • www.iiia.csic.es/People/enric/AICom.html • www.cse.lehigh.edu/~munoz/CSE335/ • www.aic.nrl.navy.mil/~aha/slides/ • http://www.csi.ucd.ie/users/barry-smyth • http://www.csi.ucd.ie/users/lorraine-mcginty

  2. Outline • Lehigh University • The InSyTe Laboratory • Overview of Case-Based Reasoning • Similarity • Retrieval • Adaptation • Conversational Case-based reasoning • Diversity versus Similarity • General versus Episodic Knowledge • Final Remarks

  3. Synthetizing Diversity • Showcasing diverse solutions: success story in recommender systems (Smyth, Burke, McGinty …) • Plan diversity: • Definition of the problem: quantitative vsqualitiative (Myers, AAAI-01) • Generating two or more quantitative different plans for same problem (Srivastava et al, IJCAI-07) • Synthetizing diversity: • Case-based retrieval and adaptation from plan library (Coman& Munoz-Avila, ICCBR-10; 11 – under review ) • Generating two or more qualitatively different plans for same problem (Coman & Munoz-Avila, AAAI-11) • Our common solution: • S: diverse solutions so far, s: candidate solution, P: new problem sim(s,P) + relativeDiversity(s,S) • What changes: S, s, P, sim(), D(s,s’) 11

  4. Research Program: Synthetizing Diversity preliminary work: Plan Diversity Case-based plan diversity sim(s,P) + relativeDiversity(s,S) New insight: sim(s,P) + relativeDiversity(s,S) + cost(s) Proposed idea: • Representation scope of using D() versus qualitative diversity • Trade-offs of solution: • Diversity versus quality • Diversity versus generation • Diversity in other paradigms: search (A*) Research topics: Danger: don’t want it to be a planning proposal

  5. Focus Point: Diversity in CBR

  6. Query Available case Similar case Traditional Retrieval Approach • Similarity-BasedRetrieval • Select the k most similar items to the current query. • Problem • Vague queries. • Limited coverage of search space in every cycle of the dialogue. C2 C3 C1 Q

  7. Query Available case Retrieved case Diversity Enhancement • Diversity-EnhancedRetrieval • Select k items such that they are both similar to the current query but different from each other. • Providing a wider choice allows for broader coverage of the product space. • Allows many less relevant items to be eliminated. C1 Q C2 C3

  8. Dangers of Diversity Enhancement • Leap-Frogging the Target • Problems occur when the target product is rejected as a retrieval candidate on diversity grounds. •  Protracted dialogs. • Diversity is problematic in the region of the target product. • Use similarity for fine-grained search. • Similarity is problematic when far from the target product. • Use diversity to speed-up the search. T C1 Q C2 C3

  9. Final Remarks

  10. Questions?

More Related