1 / 46

Semi-Supervised Learning

Semi-Supervised Learning. Jia-Bin Huang Virginia Tech. ECE-5424G / CS-5824. Spring 2019. Administrative. HW 4 due April 10. Recommender Systems. Motivation Problem formulation Content-based recommendations Collaborative filtering Mean normalization. Problem motivation.

hturner
Télécharger la présentation

Semi-Supervised Learning

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. Semi-Supervised Learning Jia-Bin Huang Virginia Tech ECE-5424G / CS-5824 Spring 2019

  2. Administrative • HW 4 due April 10

  3. Recommender Systems • Motivation • Problem formulation • Content-based recommendations • Collaborative filtering • Mean normalization

  4. Problem motivation

  5. Problem motivation

  6. Optimization algorithm • Given , to learn : • Given , to learn :

  7. Collaborative filtering • Given (and movie ratings), Can estimate • Given Can estimate

  8. Collaborative filtering optimization objective • Given , estimate • Given , estimate

  9. Collaborative filtering optimization objective • Given , estimate • Given , estimate • Minimize and simultaneously

  10. Collaborative filtering optimization objective

  11. Collaborative filtering algorithm • Initialize to small random values • Minimize using gradient descent (or an advanced optimization algorithm). For every • For a user with parameter and movie with (learned) feature , predict a star rating of

  12. Collaborative filtering

  13. Collaborative filtering • Predicted ratings: Low-rank matrix factorization

  14. Finding related movies/products • For each product , we learn a feature vector : romance, : action, : comedy, … • How to find movie relate to movie ? Small movie j and I are “similar”

  15. Recommender Systems • Motivation • Problem formulation • Content-based recommendations • Collaborative filtering • Mean normalization

  16. Users who have not rated any movies

  17. Users who have not rated any movies

  18. Mean normalization For user , on movie predict: User 5 (Eve): Learn

  19. Recommender Systems • Motivation • Problem formulation • Content-based recommendations • Collaborative filtering • Mean normalization

  20. Review: Supervised Learning • K nearest neighbor • Linear Regression • Naïve Bayes • Logistic Regression • Support Vector Machines • Neural Networks

  21. Review: Unsupervised Learning • Clustering, K-Mean • Expectation maximization • Dimensionality reduction • Anomaly detection • Recommendation system

  22. Advanced Topics • Semi-supervised learning • Probabilistic graphical models • Generative models • Sequence prediction models • Deep reinforcement learning

  23. Semi-supervised Learning • Motivation • Problem formulation • Consistency regularization • Entropy-based method • Pseudo-labeling

  24. Semi-supervised Learning • Motivation • Problem formulation • Consistency regularization • Entropy-based method • Pseudo-labeling

  25. Classic Paradigm Insufficient Nowadays • Modern applications: massive amounts of raw data. • Only a tiny fraction can be annotated by human experts Protein sequences Billions of webpages Images

  26. Semi-supervised Learning

  27. Active Learning

  28. Semi-supervised Learning • Motivation • Problem formulation • Consistency regularization • Entropy-based method • Pseudo-labeling

  29. Semi-supervised Learning Problem Formulation • Labeled data • Unlabeled data • Goal: Learn a hypothesis (e.g., a classifier) that has small error

  30. Combining labeled and unlabeled data- Classical methods • Transductive SVM [Joachims ’99] • Co-training [Blum and Mitchell ’98] • Graph-based methods [Blum and Chawla ‘01] [Zhu, Ghahramani, Lafferty ‘03]

  31. Transductive SVM • The separator goes through low density regions of the space / large margin

  32. Transductive SVM Inputs: SVM Inputs:

  33. TransductiveSVMs • First maximize margin over the labeled points • Use this to give initial labels to unlabeled points based on this separator. • Try flipping labels of unlabeled points to see if doing so can increase margin

  34. Deep Semi-supervised Learning

  35. Semi-supervised Learning • Motivation • Problem formulation • Consistency regularization • Entropy-based method • Pseudo-labeling

  36. Stochastic Perturbations/Π-Model • Realistic perturbations of data points should not significantly change the output of

  37. Temporal Ensembling

  38. Mean Teacher

  39. Virtual Adversarial Training

  40. Semi-supervised Learning • Motivation • Problem formulation • Consistency regularization • Entropy-based method • Pseudo-labeling

  41. EntMin • Encourages more confident predictions on unlabeled data.

  42. Semi-supervised Learning • Motivation • Problem formulation • Consistency regularization • Entropy-based method • Pseudo-labeling

  43. Comparison

  44. Varying number of labels

  45. Class mismatch in Labeled/Unlabeled datasets hurts the performance

  46. Lessons • Standardized architecture + equal budget for tuning hyperparameters • Unlabeled data from a different class distribution not that useful • Most methods don’t work well in the very low labeled-data regime • Transferring Pre-Trained Imagenet produces lower error rate • Conclusions based on small datasets though

More Related