SlideShare une entreprise Scribd logo
1  sur  24
Télécharger pour lire hors ligne
Self-Adaptation of
Online Recommender Systems
via Feed-Forward Controllers

Licia Capra
University College London



Workshop on Self-Awareness in Computing
June 27th, 2010
RECOMMENDER SYSTEMS
SCENARIO




   Web 2.0 Recommender Systems (CiteULike)
RECOMMENDER SYSTEMS

                      items




                      ratings




users
RECOMMENDER SYSTEMS

                      items




                      ratings




users
WEB 2.0 RECOMMENDER SYSTEMS
RECOMMENDER SYSTEMS (Web 2.0)

                         items




                         tags




users
RECOMMENDER SYSTEMS
    i    j   k   l    m
a
b
c
d
        User x Item
PROBLEM
DOMAIN PROBLEM ANALYSIS
  Dataset: Bibsonomy
  •  1.3k users; 24k items; 12k tags; 73k bookmarks
              5/+72<"
         )!!!!"




         (!!!!"
                                   *++,-./,0"

                                   123-0"
         '!!!!"
                                   4.50"

                                   603/0"
         &!!!!"




         %!!!!"

                                                                                  123-0"5/+7"8.023/"
         $!!!!"




         #!!!!"


                                                              4.50"5/+7"8.023/"
             !"
                  #"    ("   ##"            #("   $#"   $("          %#"      %("         &#"      &("           '#"
                                                                                                         9-3":-+;2<0="
DOMAIN PROBLEM ANALYSIS
  Method of Assessment
   Time	
  	
   User	
   Tag	
   Item	
  
  Period	
  
    T1	
         6%	
        17%	
              2%	
  
    T2	
         6%	
        1%	
               11%	
  
    T3	
         6%	
        2%	
               3%	
  


                                       Ti	
               1500	
  tests	
  



     Training	
  Ti(1)	
  
                      Training	
  Ti(2)	
  
DOMAIN PROBLEM ANALYSIS
  Method of Assessment
   Time	
  	
   User	
   Tag	
   Item	
                       Accuracy	
  Loss	
   Accuracy	
  Loss	
   Accuracy	
  Loss	
  
  Period	
                                                       (25-­‐75)	
          (50-­‐50)	
          (75-­‐25)	
  
    T1	
         6%	
        17%	
              2%	
                  24%	
              32%	
                 45%	
  
    T2	
         6%	
        1%	
               11%	
                 12%	
              20%	
                 23%	
  
    T3	
         6%	
        2%	
               3%	
                   3%	
              10%	
                 14%	
  


                                       Ti	
               1500	
  tests	
  



     Training	
  Ti(1)	
  
                      Training	
  Ti(2)	
  
DOMAIN PROBLEM ANALYSIS
  Method of Assessment
   Time	
  	
   User	
   Tag	
   Item	
                       Accuracy	
  Loss	
   Accuracy	
  Loss	
   Accuracy	
  Loss	
  
  Period	
                                                       (25-­‐75)	
          (50-­‐50)	
          (75-­‐25)	
  
    T1	
         6%	
        17%	
              2%	
                  24%	
              32%	
                 45%	
  
    T2	
         6%	
        1%	
               11%	
                 12%	
              20%	
                 23%	
  
    T3	
         6%	
        2%	
               3%	
                   3%	
              10%	
                 14%	
  


                                       Ti	
               1500	
  tests	
  



     Training	
  Ti(1)	
  
                      Training	
  Ti(2)	
  
IDEA
DYNAMIC UPDATE METHODOLOGY
  Recommender Systems as Self-Adaptive
   Systems
                x	
  
       [users,items,tags]	
       [Recommender	
  ]                    y	
  
                                      System	
          [recommendaFon	
  	
  
                                                                   list]	
  

                         u	
  
      [update	
  frequency]	
  


                                            Feed-­‐Back	
  
DYNAMIC UPDATE METHODOLOGY
  Feed-Forward Controller for Dynamic
   Updating of Recommender Systems

                       x	
  
              [users,items,tags]	
        [Recommender	
  ]                  y	
  
                                                              [recommendaFon	
  	
  
                          u	
                 System	
                   list]	
  
              [update	
  frequency]	
  




     Feed-­‐Forward	
  
DOES IT WORK?
EVALUATION
  Empirical Estimate of Performance Loss
     ./01232456/01788#8433#
     (&"#



     (%"#



     ($"#



     (!"#

                                                                                            +*"-$*"#
      '"#                                                                                   *!"-*!"#
                                                                                            $*"-+*"#

      &"#



      %"#



      $"#



      !"#
                ("#           $"#   )"#   %"#   *"#   &"#   +"#   '"#   ,"#   (!"#   9/4:;<#/7;0#
EVALUATION
  Cumulative Error (50-50 test set)
 '#"




 '!"




  &"



                                                                                                           +,-./01"

  %"                                                                                                       2345678")9"
                                                                                                           2345678"#9"
                                                                                                           :88;01"


  $"




  #"




  !"
       '"   %"   ''"   '%"   #'"   #%"   ('"   (%"   $'"   $%"   )'"   )%"   %'"   %%"   *'"   *%"   &'"
EVALUATION
  Cumulative Error & N. of Updates

                                                                                                                          Technique    N. Of Updates
 '#"




 '!"

                                                                                                                           Weekly           80
  &"




                                                                                                                         Adaptive 2%        29
                                                                                                           +,-./01"

  %"                                                                                                       2345678")9"
                                                                                                           2345678"#9"
                                                                                                           :88;01"


  $"




  #"
                                                                                                                         Adaptive 5%        13
  !"
       '"   %"   ''"   '%"   #'"   #%"   ('"   (%"   $'"   $%"   )'"   )%"   %'"   %%"   *'"   *%"   &'"



                                                                                                                           Monthly          18
EVALUATION
  Cumulative Error & N. of Updates

                                                                                                                          Technique    N. Of Updates
 '#"




 '!"

                                                                                                                           Weekly           80
  &"




                                                                                                                         Adaptive 2%        29
                                                                                                           +,-./01"

  %"                                                                                                       2345678")9"
                                                                                                           2345678"#9"
                                                                                                           :88;01"


  $"




  #"
                                                                                                                         Adaptive 5%        13
  !"
       '"   %"   ''"   '%"   #'"   #%"   ('"   (%"   $'"   $%"   )'"   )%"   %'"   %%"   *'"   *%"   &'"



                                                                                                                           Monthly          18
CONCLUSIONS

  Accuracy vs Cost Tradeoff may
   lead to suboptimal choices
  Recommender Systems as Self-
   Adaptive Systems
  Feed-Forward Control Theory for
   Unobservable Outputs
… & FUTURE WORK
   Automation of Empirical Evaluation

   Beyond Accuracy and Cost (diversity,
    surprise, serendipity)
  On self-adaptation
   •    B.H. Cheng, et al. Software Engineering for Self-Adaptive Systems: A Research Roadmap.
        In Software Engineering for Self-Adaptive Systems, pages 1-26, 2009. Springer-Verlag
   •    Y. Brun, et al. Engineering Self-Adaptive Systems through Feedback Loops. In Software
        Engineering for Self-Adaptive Systems, pages 48-70, 2009. Springer-Verlag.
  On recommender-systems
   •    J. Herlocker, et al. An Algorithmic Framework for Performing Collaborative Filtering. In
        Proc. of the 22nd Annual International Conference on Research and Development in
        Information Retrieval, pages 230-237, New York, NY, USA, 1999. ACM.
   •    G. Adomavicius and A. Tuzhilin. Context-Aware Recommender Systems. In Proc. of the ACM
        Conference on Recommender Systems, 2008.
  From my group
   •    V. Zanardi and L. Capra. Social Ranking: Uncovering Relevant Content using Tag-based
        Recommender Systems. In Proc. of the Conference on Recommender Systems, pages
        51-58, 2008. ACM.
   •    V. Zanardi and L. Capra. "Dynamic Updating of Online Recommender Systems via Feed-
        Forward Controllers". In 6th Intl. Symposium on Software Engineering for Adaptive and
        Self-Managing Systems (SEAMS 2011). Waikiki, Honolulu, Hawaii, USA. May 2011




                           THANK YOU!

Contenu connexe

Similaire à Self-Adaptation of Online Recommender Systems via Feed-Forward Controllers

Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?
Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?
Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?Martin Ebner
 
Ben Rothke Getting A Handle On Wireless Security For Pci Dss Compliance
Ben Rothke   Getting A Handle On Wireless Security For Pci Dss ComplianceBen Rothke   Getting A Handle On Wireless Security For Pci Dss Compliance
Ben Rothke Getting A Handle On Wireless Security For Pci Dss ComplianceBen Rothke
 
Evaluating Data Freshness in Large Scale Replicated Databases
Evaluating Data Freshness in Large Scale Replicated DatabasesEvaluating Data Freshness in Large Scale Replicated Databases
Evaluating Data Freshness in Large Scale Replicated DatabasesMiguel Araújo
 
20110611 expanded intro-to_puppet_for_self
20110611 expanded intro-to_puppet_for_self20110611 expanded intro-to_puppet_for_self
20110611 expanded intro-to_puppet_for_selfgarrett honeycutt
 
WikiSym 2011 Closing Keynote
WikiSym 2011 Closing KeynoteWikiSym 2011 Closing Keynote
WikiSym 2011 Closing KeynoteEd Chi
 
Test Management by Vladimir Arutin
Test Management by Vladimir ArutinTest Management by Vladimir Arutin
Test Management by Vladimir ArutinVladimir Arutin
 
Testar2014 presentation
Testar2014 presentationTestar2014 presentation
Testar2014 presentationTanja Vos
 
The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...
The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...
The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...Julián Urbano
 
Lean Production
Lean ProductionLean Production
Lean Productionxyhfun
 
Dramatically increase revenue on verio template
Dramatically increase revenue on verio templateDramatically increase revenue on verio template
Dramatically increase revenue on verio templateJanine Soika
 
Dramatically increase revenue on verio template
Dramatically increase revenue on verio templateDramatically increase revenue on verio template
Dramatically increase revenue on verio templateJanine Soika
 
Massive device deployment - EclipseCon 2011
Massive device deployment - EclipseCon 2011Massive device deployment - EclipseCon 2011
Massive device deployment - EclipseCon 2011Angelo van der Sijpt
 
Catalogmakr teaser
Catalogmakr teaserCatalogmakr teaser
Catalogmakr teasercatalogmakr
 
Managing massive datacenters
Managing massive datacentersManaging massive datacenters
Managing massive datacenterslkanies
 
A Guide to Event-Driven SRE-inspired DevOps
A Guide to Event-Driven SRE-inspired DevOpsA Guide to Event-Driven SRE-inspired DevOps
A Guide to Event-Driven SRE-inspired DevOpsAndreas Grabner
 

Similaire à Self-Adaptation of Online Recommender Systems via Feed-Forward Controllers (20)

Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?
Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?
Can Confidence Assessment Enhance Traditional Multiple-Choice Testing?
 
Ben Rothke Getting A Handle On Wireless Security For Pci Dss Compliance
Ben Rothke   Getting A Handle On Wireless Security For Pci Dss ComplianceBen Rothke   Getting A Handle On Wireless Security For Pci Dss Compliance
Ben Rothke Getting A Handle On Wireless Security For Pci Dss Compliance
 
Evaluating Data Freshness in Large Scale Replicated Databases
Evaluating Data Freshness in Large Scale Replicated DatabasesEvaluating Data Freshness in Large Scale Replicated Databases
Evaluating Data Freshness in Large Scale Replicated Databases
 
20110611 expanded intro-to_puppet_for_self
20110611 expanded intro-to_puppet_for_self20110611 expanded intro-to_puppet_for_self
20110611 expanded intro-to_puppet_for_self
 
Statistical Process Control
Statistical Process ControlStatistical Process Control
Statistical Process Control
 
WikiSym 2011 Closing Keynote
WikiSym 2011 Closing KeynoteWikiSym 2011 Closing Keynote
WikiSym 2011 Closing Keynote
 
Test Management by Vladimir Arutin
Test Management by Vladimir ArutinTest Management by Vladimir Arutin
Test Management by Vladimir Arutin
 
Testar2014 presentation
Testar2014 presentationTestar2014 presentation
Testar2014 presentation
 
The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...
The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...
The University Carlos III of Madrid at TREC 2011 Crowdsourcing Track: Noteboo...
 
Lean Production
Lean ProductionLean Production
Lean Production
 
Pilot Interim Results
Pilot Interim ResultsPilot Interim Results
Pilot Interim Results
 
Performance tests - it's a trap
Performance tests - it's a trapPerformance tests - it's a trap
Performance tests - it's a trap
 
Dramatically increase revenue on verio template
Dramatically increase revenue on verio templateDramatically increase revenue on verio template
Dramatically increase revenue on verio template
 
Dramatically increase revenue on verio template
Dramatically increase revenue on verio templateDramatically increase revenue on verio template
Dramatically increase revenue on verio template
 
Massive device deployment - EclipseCon 2011
Massive device deployment - EclipseCon 2011Massive device deployment - EclipseCon 2011
Massive device deployment - EclipseCon 2011
 
Device deployment
Device deploymentDevice deployment
Device deployment
 
Catalogmakr teaser
Catalogmakr teaserCatalogmakr teaser
Catalogmakr teaser
 
Managing massive datacenters
Managing massive datacentersManaging massive datacenters
Managing massive datacenters
 
1b7 quality control
1b7 quality control1b7 quality control
1b7 quality control
 
A Guide to Event-Driven SRE-inspired DevOps
A Guide to Event-Driven SRE-inspired DevOpsA Guide to Event-Driven SRE-inspired DevOps
A Guide to Event-Driven SRE-inspired DevOps
 

Plus de FET AWARE project - Self Awareness in Autonomic Systems

Plus de FET AWARE project - Self Awareness in Autonomic Systems (20)

Academic Course: 13 Applications of and Challenges in Self-Awareness
Academic Course: 13 Applications of and Challenges in Self-AwarenessAcademic Course: 13 Applications of and Challenges in Self-Awareness
Academic Course: 13 Applications of and Challenges in Self-Awareness
 
Academic Course: 12 Safety and Ethics
Academic Course: 12 Safety and EthicsAcademic Course: 12 Safety and Ethics
Academic Course: 12 Safety and Ethics
 
Academic Course: 08 Pattern-based design of autonomic systems
Academic Course: 08 Pattern-based design of autonomic systemsAcademic Course: 08 Pattern-based design of autonomic systems
Academic Course: 08 Pattern-based design of autonomic systems
 
Academic Course: 07 Introduction to the Formal Engineering of Autonomic Systems
Academic Course: 07 Introduction to the Formal Engineering of Autonomic SystemsAcademic Course: 07 Introduction to the Formal Engineering of Autonomic Systems
Academic Course: 07 Introduction to the Formal Engineering of Autonomic Systems
 
Academic Course: 06 Morphogenetic Engineering
Academic Course: 06 Morphogenetic EngineeringAcademic Course: 06 Morphogenetic Engineering
Academic Course: 06 Morphogenetic Engineering
 
Academic Course: 04 Introduction to complex systems and agent based modeling
Academic Course: 04 Introduction to complex systems and agent based modelingAcademic Course: 04 Introduction to complex systems and agent based modeling
Academic Course: 04 Introduction to complex systems and agent based modeling
 
Academic Course: 03 Autonomic Multi-Agent Systems
Academic Course: 03 Autonomic Multi-Agent SystemsAcademic Course: 03 Autonomic Multi-Agent Systems
Academic Course: 03 Autonomic Multi-Agent Systems
 
Academic Course: 02 Self-organization and emergence in networked systems
Academic Course: 02 Self-organization and emergence in networked systemsAcademic Course: 02 Self-organization and emergence in networked systems
Academic Course: 02 Self-organization and emergence in networked systems
 
Academic Course: 01 Self-awarenesss and Computational Self-awareness
Academic Course: 01 Self-awarenesss and Computational Self-awarenessAcademic Course: 01 Self-awarenesss and Computational Self-awareness
Academic Course: 01 Self-awarenesss and Computational Self-awareness
 
Awareness: Layman Seminar Slides
Awareness: Layman Seminar SlidesAwareness: Layman Seminar Slides
Awareness: Layman Seminar Slides
 
Industry Training: 04 Awareness Applications
Industry Training: 04 Awareness ApplicationsIndustry Training: 04 Awareness Applications
Industry Training: 04 Awareness Applications
 
Industry Training: 03 Awareness Simulation
Industry Training: 03 Awareness SimulationIndustry Training: 03 Awareness Simulation
Industry Training: 03 Awareness Simulation
 
Industry Training: 02 Awareness Properties
Industry Training: 02 Awareness PropertiesIndustry Training: 02 Awareness Properties
Industry Training: 02 Awareness Properties
 
Industry Training: 01 Awareness Overview
Industry Training: 01 Awareness OverviewIndustry Training: 01 Awareness Overview
Industry Training: 01 Awareness Overview
 
Robot Swarms as Ensembles of Cooperating Components - Matthias Holzl
Robot Swarms as Ensembles of Cooperating Components - Matthias HolzlRobot Swarms as Ensembles of Cooperating Components - Matthias Holzl
Robot Swarms as Ensembles of Cooperating Components - Matthias Holzl
 
Towards Systematically Engineering Ensembles - Martin Wirsing
Towards Systematically Engineering Ensembles - Martin WirsingTowards Systematically Engineering Ensembles - Martin Wirsing
Towards Systematically Engineering Ensembles - Martin Wirsing
 
Capturing the Immune System: From the wet-­lab to the robot, building better ...
Capturing the Immune System: From the wet-­lab to the robot, building better ...Capturing the Immune System: From the wet-­lab to the robot, building better ...
Capturing the Immune System: From the wet-­lab to the robot, building better ...
 
Underwater search and rescue in swarm robotics - Mark Read
Underwater search and rescue in swarm robotics - Mark Read Underwater search and rescue in swarm robotics - Mark Read
Underwater search and rescue in swarm robotics - Mark Read
 
Computational Self-awareness in Smart-Camera Networks - Lukas Esterle
Computational Self-awareness in Smart-Camera Networks - Lukas EsterleComputational Self-awareness in Smart-Camera Networks - Lukas Esterle
Computational Self-awareness in Smart-Camera Networks - Lukas Esterle
 
Why Robots may need to be self-­‐aware, before we can really trust them - Ala...
Why Robots may need to be self-­‐aware, before we can really trust them - Ala...Why Robots may need to be self-­‐aware, before we can really trust them - Ala...
Why Robots may need to be self-­‐aware, before we can really trust them - Ala...
 

Dernier

Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxheathfieldcps1
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSCeline George
 
Dyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptxDyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptxcallscotland1987
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
Third Battle of Panipat detailed notes.pptx
Third Battle of Panipat detailed notes.pptxThird Battle of Panipat detailed notes.pptx
Third Battle of Panipat detailed notes.pptxAmita Gupta
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17Celine George
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentationcamerronhm
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...Nguyen Thanh Tu Collection
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and ModificationsMJDuyan
 
PROCESS RECORDING FORMAT.docx
PROCESS      RECORDING        FORMAT.docxPROCESS      RECORDING        FORMAT.docx
PROCESS RECORDING FORMAT.docxPoojaSen20
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxVishalSingh1417
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...pradhanghanshyam7136
 
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptxSKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptxAmanpreet Kaur
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsTechSoup
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsMebane Rash
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...christianmathematics
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.MaryamAhmad92
 

Dernier (20)

Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
Asian American Pacific Islander Month DDSD 2024.pptx
Asian American Pacific Islander Month DDSD 2024.pptxAsian American Pacific Islander Month DDSD 2024.pptx
Asian American Pacific Islander Month DDSD 2024.pptx
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POS
 
Dyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptxDyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptx
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Third Battle of Panipat detailed notes.pptx
Third Battle of Panipat detailed notes.pptxThird Battle of Panipat detailed notes.pptx
Third Battle of Panipat detailed notes.pptx
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentation
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
PROCESS RECORDING FORMAT.docx
PROCESS      RECORDING        FORMAT.docxPROCESS      RECORDING        FORMAT.docx
PROCESS RECORDING FORMAT.docx
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
 
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptxSKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 

Self-Adaptation of Online Recommender Systems via Feed-Forward Controllers

  • 1. Self-Adaptation of Online Recommender Systems via Feed-Forward Controllers Licia Capra University College London Workshop on Self-Awareness in Computing June 27th, 2010
  • 3. SCENARIO Web 2.0 Recommender Systems (CiteULike)
  • 4. RECOMMENDER SYSTEMS items ratings users
  • 5. RECOMMENDER SYSTEMS items ratings users
  • 7. RECOMMENDER SYSTEMS (Web 2.0) items tags users
  • 8. RECOMMENDER SYSTEMS i j k l m a b c d User x Item
  • 10. DOMAIN PROBLEM ANALYSIS   Dataset: Bibsonomy •  1.3k users; 24k items; 12k tags; 73k bookmarks 5/+72<" )!!!!" (!!!!" *++,-./,0" 123-0" '!!!!" 4.50" 603/0" &!!!!" %!!!!" 123-0"5/+7"8.023/" $!!!!" #!!!!" 4.50"5/+7"8.023/" !" #" (" ##" #(" $#" $(" %#" %(" &#" &(" '#" 9-3":-+;2<0="
  • 11. DOMAIN PROBLEM ANALYSIS   Method of Assessment Time     User   Tag   Item   Period   T1   6%   17%   2%   T2   6%   1%   11%   T3   6%   2%   3%   Ti   1500  tests   Training  Ti(1)   Training  Ti(2)  
  • 12. DOMAIN PROBLEM ANALYSIS   Method of Assessment Time     User   Tag   Item   Accuracy  Loss   Accuracy  Loss   Accuracy  Loss   Period   (25-­‐75)   (50-­‐50)   (75-­‐25)   T1   6%   17%   2%   24%   32%   45%   T2   6%   1%   11%   12%   20%   23%   T3   6%   2%   3%   3%   10%   14%   Ti   1500  tests   Training  Ti(1)   Training  Ti(2)  
  • 13. DOMAIN PROBLEM ANALYSIS   Method of Assessment Time     User   Tag   Item   Accuracy  Loss   Accuracy  Loss   Accuracy  Loss   Period   (25-­‐75)   (50-­‐50)   (75-­‐25)   T1   6%   17%   2%   24%   32%   45%   T2   6%   1%   11%   12%   20%   23%   T3   6%   2%   3%   3%   10%   14%   Ti   1500  tests   Training  Ti(1)   Training  Ti(2)  
  • 14. IDEA
  • 15. DYNAMIC UPDATE METHODOLOGY   Recommender Systems as Self-Adaptive Systems x   [users,items,tags]   [Recommender  ] y   System   [recommendaFon     list]   u   [update  frequency]   Feed-­‐Back  
  • 16. DYNAMIC UPDATE METHODOLOGY   Feed-Forward Controller for Dynamic Updating of Recommender Systems x   [users,items,tags]   [Recommender  ] y   [recommendaFon     u   System   list]   [update  frequency]   Feed-­‐Forward  
  • 18. EVALUATION   Empirical Estimate of Performance Loss ./01232456/01788#8433# (&"# (%"# ($"# (!"# +*"-$*"# '"# *!"-*!"# $*"-+*"# &"# %"# $"# !"# ("# $"# )"# %"# *"# &"# +"# '"# ,"# (!"# 9/4:;<#/7;0#
  • 19. EVALUATION   Cumulative Error (50-50 test set) '#" '!" &" +,-./01" %" 2345678")9" 2345678"#9" :88;01" $" #" !" '" %" ''" '%" #'" #%" ('" (%" $'" $%" )'" )%" %'" %%" *'" *%" &'"
  • 20. EVALUATION   Cumulative Error & N. of Updates Technique N. Of Updates '#" '!" Weekly 80 &" Adaptive 2% 29 +,-./01" %" 2345678")9" 2345678"#9" :88;01" $" #" Adaptive 5% 13 !" '" %" ''" '%" #'" #%" ('" (%" $'" $%" )'" )%" %'" %%" *'" *%" &'" Monthly 18
  • 21. EVALUATION   Cumulative Error & N. of Updates Technique N. Of Updates '#" '!" Weekly 80 &" Adaptive 2% 29 +,-./01" %" 2345678")9" 2345678"#9" :88;01" $" #" Adaptive 5% 13 !" '" %" ''" '%" #'" #%" ('" (%" $'" $%" )'" )%" %'" %%" *'" *%" &'" Monthly 18
  • 22. CONCLUSIONS   Accuracy vs Cost Tradeoff may lead to suboptimal choices   Recommender Systems as Self- Adaptive Systems   Feed-Forward Control Theory for Unobservable Outputs
  • 23. … & FUTURE WORK   Automation of Empirical Evaluation   Beyond Accuracy and Cost (diversity, surprise, serendipity)
  • 24.   On self-adaptation •  B.H. Cheng, et al. Software Engineering for Self-Adaptive Systems: A Research Roadmap. In Software Engineering for Self-Adaptive Systems, pages 1-26, 2009. Springer-Verlag •  Y. Brun, et al. Engineering Self-Adaptive Systems through Feedback Loops. In Software Engineering for Self-Adaptive Systems, pages 48-70, 2009. Springer-Verlag.   On recommender-systems •  J. Herlocker, et al. An Algorithmic Framework for Performing Collaborative Filtering. In Proc. of the 22nd Annual International Conference on Research and Development in Information Retrieval, pages 230-237, New York, NY, USA, 1999. ACM. •  G. Adomavicius and A. Tuzhilin. Context-Aware Recommender Systems. In Proc. of the ACM Conference on Recommender Systems, 2008.   From my group •  V. Zanardi and L. Capra. Social Ranking: Uncovering Relevant Content using Tag-based Recommender Systems. In Proc. of the Conference on Recommender Systems, pages 51-58, 2008. ACM. •  V. Zanardi and L. Capra. "Dynamic Updating of Online Recommender Systems via Feed- Forward Controllers". In 6th Intl. Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS 2011). Waikiki, Honolulu, Hawaii, USA. May 2011 THANK YOU!