moderated class membership interchange in relational
play

Moderated Class-membership Interchange in Relational Classification - PowerPoint PPT Presentation

Moderated Class-membership Interchange in Relational Classification Peter Vojtek, Mria Bielikov Slovak University of Technology in Bratislava Faculty of Informatics and Information Technologies Bratislava, Slovakia Relational (collective)


  1. Moderated Class-membership Interchange in Relational Classification Peter Vojtek, Mária Bieliková Slovak University of Technology in Bratislava Faculty of Informatics and Information Technologies Bratislava, Slovakia

  2. Relational (collective) classification Sort new scientific articles into two classes : • articles concerning Hardware • articles concerning Software

  3. Relational (collective) classification Sort new scientific articles into two classes : • articles concerning Hardware • articles concerning Software article text

  4. Relational (collective) classification Sort new scientific articles into two classes : • articles concerning Hardware • articles concerning Software article keyword author � text

  5. Relational (collective) classification Sort new scientific articles into two classes : • articles concerning Hardware • articles concerning Software article keyword author � relation: relation: hasKeyword hasAuthor text

  6. Relational (collective) classification Sort new scientific articles into two classes : • articles concerning Hardware • articles concerning Software article keyword author � relation: relation: hasKeyword hasAuthor text relation: references

  7. Collective Inferencing • classmembership of each instance is initialized – Article No.1: [Hardware: 80%, Software: 20%] – Article No.2: [Hardware: 50%, Software: 50%]

  8. Collective Inferencing • classmembership of each instance is initialized – Article No.1: [Hardware: 80%, Software: 20%] – Article No.2: [Hardware: 50%, Software: 50%] • neighbouring instances share and update their • neighbouring instances share and update their classmemberships • iterative, convergent process • at the end – Article No.1: [Hardware: 91%, Software: 9%] is assignet to class Hardware

  9. Mis classification real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes

  10. Mis classification real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes HW 55% HW 30% HW 30% HW HW SW 45% SW 45% SW 70% article article article

  11. Mis classification real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes HW 55% HW 30% HW 30% HW HW SW 45% SW 45% SW 70% article article article HW 40% HW 30% HW SW 60% SW 70% article article article

  12. real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes HW 55% HW 30% HW SW 45% SW 70% article article article HW 40% HW 30% HW SW 60% SW 70% article article article HW 70% HW 40% HW SW 30% SW 60% article article article

  13. real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes HW 55% HW 30% HW SW 45% SW 70% article article article HW 40% HW 30% HW SW 60% SW 70% article article article HW 70% HW 40% HW SW 30% SW 60% article article article

  14. real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes HW 55% HW 30% HW SW 45% SW 70% article article article HW 40% HW 30% HW SW 60% SW 70% article article article HW 70% HW 40% HW SW 30% SW 60% article article article

  15. real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes HW 55% HW 30% HW SW 45% SW 70% article article article HW 40% HW 30% ? HW SW 60% SW 70% article article article HW 70% HW 40% HW SW 30% SW 60% article article article

  16. real class initial classmembership final classmembership HW 70% HW 80% HW SW 30% SW 20% article article article Naïve collective inference Bayes HW 55% HW 30% HW SW 45% SW 70% article article article HW 40% HW 30% ? HW SW 60% SW 70% article article article HW 70% HW 40% HW SW 30% SW 60% article article article

  17. Information Exchange Moderation • Classmembership is evaluated using entropy HW 100% – great value : [hardware: 100%, software: 0%] SW 0% – worthless: [hardware: 50%, software: 50%] accept ignore 50 : 50 0 : 100 hardware : software

  18. Information Exchange Moderation • Classmembership is evaluated using entropy – great value : [hardware: 100%, software: 0%] – worthless: [hardware: 50%, software: 50%] threshold moderation accept ignore 50 : 50 0 : 100 hardware : software

  19. Information Exchange Moderation • Classmembership is evaluated using entropy – great value : [hardware: 100%, software: 0%] – worthless: [hardware: 50%, software: 50%] linear continuous moderation accept ignore 50 : 50 0 : 100 hardware : software

  20. Experimental Evaluation • MAPEKUS dataset http://mapekus.fiit.stuba.sk • two accuracy values are compared : – accuracy after initialization (naïve Bayes based on text of article’s abstract) (naïve Bayes based on text of article’s abstract) – accuracy after collective inferencing

  21. Experimental Evaluation 10 Initialization: 8 • 80% accuracy y Gain [%] Collective inferencing: 6 • 89% accuracy Accuracy G 4 ACM classes: General 2 Literature Software 0 Data -2 0,5 0,55 0,6 0,65 0,7 0,75 0,8 0,85 0,9 0,95 1 Direct class No moderation Moderation Threshold Assigment only

  22. Experimental Evaluation 10 Initialization: 8 • 80% accuracy y Gain [%] Collective inferencing: 6 • 89% accuracy Accuracy G 4 ACM classes: General 2 Literature Software 0 Data -2 0,5 0,55 0,6 0,65 0,7 0,75 0,8 0,85 0,9 0,95 1 Direct class No moderation Moderation Threshold Assigment only accept ignore

  23. Conclusions • new method to increase robustness of relational classification • succesfully evaluated on – MAPEKUS dataset – MAPEKUS dataset – (Netflix+IMDB) movie recommendation • further work: – different shapes of moderation function – shift to homophily

Recommend


More recommend