PEBL: Web Page Classification without Negative Examples

1
PEBL Web Page Classification without Negative
Examples

• Hwanjo Yu, Jiawei Han, Kevin Chen-Chuan Chang

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA
ENGINEERING, JAN 2004
2
Outline

• Problem statement
• Motivation
• Related work
• Main contribution
• Technical details
• Experiments
• Summary

3
Problem Statement

• To classify web pages into user-interesting
  classes.
• E.g. Home-Page Classifier Call for Papers
  Classifier
• Negative Samples are not given specifically.
• Positive and Unlabeled Samples.

4
Motivation

• Collecting Negative Samples may be delicate and
  arduous
• Negative samples must uniformly represent the
  universal set.
• Manually collected negative training examples
  could be biased.
• Predefined classes usually do not match users
  diverse and changing search targets.

5
Challenges

• Collecting unbiased unlabeled data from universal
  set.
• Random Sampling of web pages on Internet.
• Achieving classification accuracy from positive
  unlabeled data as high as from labeled data.
• PEBL framework (Mapping-Convergence Algorithm
  using SVM).

6
Related Work

• Semisupervised Learning
• Requires sample of labeled (/-) and unlabeled
  data
• EM algorithm
• Transductive SVM
• Single-Class Learning or Classification
• Rule-based (k-DNF)
• Not tolerant to sparse, high-dimensionality.
• Requires knowledge of proportion of positive
  instances in the universal set.
• Probability-based
• Requires prior probabilities for each class.
• Assumes linear separation.
• OSVM, Neural Networks

7
Main Contribution

• Collection of just positive samples speeds up the
  process of building classifiers.
• The universal set of unlabeled samples can be
  reused for training different classifiers.
• This supports example based query on internet.
• PEBL achieves accuracy as high as that of a
  typical framework w/o loss of efficiency in
  testing.

8
(No Transcript)
9
SVM Overview
10
Mapping-Convergence Algorithm

• Mapping Stage
• A weak classifier (?1) that draws an initial
  approximation of strong negative data.
• ?1 must not generate false negatives.
• Convergence Stage
• Runs in iteration using a second base classifier
  (?2) that maximizes the margin to make
  progressively better approximation of negative
  data.
• ?2 must maximize margin.

11
Mapping Stage
12
Mapping-Convergence Algorithm
13
Mapping-Convergence Algorithm
14
Experiments

• LIBSVM for SVM implementation.
• Gaussian Kernels for better text categorization
  accuracy.
• Experiment1 The Internet
• 2388 pages from DMOZ - unlabeled dataset
• 368 personal homepages, 449 non-homepages
• 192 college admission pages, 450 non-admission
• 188 resume pages, 533 non-resume pages

15
Experiments

• Experiment2 University CS Department
• 4093 pages from WebKB - unlabeled dataset
• 1641 student pages, 662 non-student pages
• 504 project pages, 753 non-project pages
• 1124 faculty pages, 729 non-faculty pages
• Precision-Recall (P-R) breakeven point is used as
  the performance measure.
• Compared against
• TSVM Traditional SVM
• OSVM One-Class SVM
• UN treating unlabeled data as negative instances

16
Experiments
17
Experiments
18
Summary

• Classifying web pages of interesting class
  requires laborious preprocessing.
• PEBL framework eliminates the need for negative
  training samples.
• M-C algorithm achieves accuracy as high as
  traditional SVM.
• Additional multiplicative logarithmic factor in
  training time on top of SVM.

19
End of Show