On Appropriate Assumptions to Mine Data Streams: Analyses and Solutions Jing Gao† Wei Fan‡ Jiawei Han† †University of Illinois at Urbana-Champaign ‡IBM.

Slides:



Advertisements
Similar presentations
Wei Fan Ed Greengrass Joe McCloskey Philip S. Yu Kevin Drummey
Advertisements

A Fully Distributed Framework for Cost-sensitive Data Mining Wei Fan, Haixun Wang, and Philip S. Yu IBM T.J.Watson, Hawthorne, New York Salvatore J. Stolfo.
A Framework for Scalable Cost- sensitive Learning Based on Combining Probabilities and Benefits Wei Fan, Haixun Wang, and Philip S. Yu IBM T.J.Watson Salvatore.
Knowledge Transfer via Multiple Model Local Structure Mapping Jing Gao Wei Fan Jing JiangJiawei Han University of Illinois at Urbana-Champaign IBM T. J.
On the Optimality of Probability Estimation by Random Decision Trees Wei Fan IBM T.J.Watson.
Systematic Data Selection to Mine Concept Drifting Data Streams Wei Fan IBM T.J.Watson.
Knowledge Transfer via Multiple Model Local Structure Mapping Jing Gao, Wei Fan, Jing Jiang, Jiawei Han l Motivate Solution Framework Data Sets Synthetic.
A General Framework for Mining Concept-Drifting Data Streams with Skewed Distributions Jing Gao Wei Fan Jiawei Han Philip S. Yu University of Illinois.
Is Random Model Better? -On its accuracy and efficiency-
Decision Tree Evolution using Limited number of Labeled Data Items from Drifting Data Streams Wei Fan 1, Yi-an Huang 2, and Philip S. Yu 1 1 IBM T.J.Watson.
Classification, Regression and Other Learning Methods CS240B Presentation Peter Huang June 4, 2014.
Combining Classification and Model Trees for Handling Ordinal Problems D. Anyfantis, M. Karagiannopoulos S. B. Kotsiantis, P. E. Pintelas Educational Software.
Data Mining Classification: Alternative Techniques
Ensemble Methods An ensemble method constructs a set of base classifiers from the training data Ensemble or Classifier Combination Predict class label.
CSCI 347 / CS 4206: Data Mining Module 07: Implementations Topic 03: Linear Models.
Data Stream Classification: Training with Limited Amount of Labeled Data Mohammad Mehedy Masud Latifur Khan Bhavani Thuraisingham University of Texas at.
CMPUT 466/551 Principal Source: CMU
CS 590M Fall 2001: Security Issues in Data Mining Lecture 3: Classification.
Announcements  Homework 4 is due on this Thursday (02/27/2004)  Project proposal is due on 03/02.
Ensemble Learning: An Introduction
Heterogeneous Consensus Learning via Decision Propagation and Negotiation Jing Gao † Wei Fan ‡ Yizhou Sun † Jiawei Han † †University of Illinois at Urbana-Champaign.
Heterogeneous Consensus Learning via Decision Propagation and Negotiation Jing Gao† Wei Fan‡ Yizhou Sun†Jiawei Han† †University of Illinois at Urbana-Champaign.
Novel Self-Configurable Positioning Technique for Multihop Wireless Networks Authors : Hongyi Wu Chong Wang Nian-Feng Tzeng IEEE/ACM TRANSACTIONS ON NETWORKING,
1 Ensembles of Nearest Neighbor Forecasts Dragomir Yankov, Eamonn Keogh Dept. of Computer Science & Eng. University of California Riverside Dennis DeCoste.
Knowledge Transfer via Multiple Model Local Structure Mapping Jing Gao† Wei Fan‡ Jing Jiang†Jiawei Han† †University of Illinois at Urbana-Champaign ‡IBM.
Machine Learning: Ensemble Methods
General Mining Issues a.j.m.m. (ton) weijters Overfitting Noise and Overfitting Quality of mined models (some figures are based on the ML-introduction.
Review Rong Jin. Comparison of Different Classification Models  The goal of all classifiers Predicating class label y for an input x Estimate p(y|x)
CSCI 347 / CS 4206: Data Mining Module 04: Algorithms Topic 06: Regression.
For Better Accuracy Eick: Ensemble Learning
Graph-based consensus clustering for class discovery from gene expression data Zhiwen Yum, Hau-San Wong and Hongqiang Wang Bioinformatics, 2007.
CS490D: Introduction to Data Mining Prof. Chris Clifton April 14, 2004 Fraud and Misuse Detection.
Learning with Positive and Unlabeled Examples using Weighted Logistic Regression Wee Sun Lee National University of Singapore Bing Liu University of Illinois,
Topics on Final Perceptrons SVMs Precision/Recall/ROC Decision Trees Naive Bayes Bayesian networks Adaboost Genetic algorithms Q learning Not on the final:
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
1 Logistic Regression Adapted from: Tom Mitchell’s Machine Learning Book Evan Wei Xiang and Qiang Yang.
Graph-based Consensus Maximization among Multiple Supervised and Unsupervised Models Jing Gao 1, Feng Liang 2, Wei Fan 3, Yizhou Sun 1, Jiawei Han 1 1.
Page 1 Ming Ji Department of Computer Science University of Illinois at Urbana-Champaign.
CSE 446 Perceptron Learning Winter 2012 Dan Weld Some slides from Carlos Guestrin, Luke Zettlemoyer.
CS 782 – Machine Learning Lecture 4 Linear Models for Classification  Probabilistic generative models  Probabilistic discriminative models.
Empirical Research Methods in Computer Science Lecture 7 November 30, 2005 Noah Smith.
CSE 446 Logistic Regression Winter 2012 Dan Weld Some slides from Carlos Guestrin, Luke Zettlemoyer.
Combining multiple learners Usman Roshan. Bagging Randomly sample training data Determine classifier C i on sampled data Goto step 1 and repeat m times.
Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.
Ensembles. Ensemble Methods l Construct a set of classifiers from training data l Predict class label of previously unseen records by aggregating predictions.
Ensemble Learning Spring 2009 Ben-Gurion University of the Negev.
Learning with AdaBoost
1 Data Mining: Concepts and Techniques (3 rd ed.) — Chapter 12 — Jiawei Han, Micheline Kamber, and Jian Pei University of Illinois at Urbana-Champaign.
INTRODUCTION TO Machine Learning 3rd Edition
Chapter1: Introduction Chapter2: Overview of Supervised Learning
Consensus Extraction from Heterogeneous Detectors to Improve Performance over Network Traffic Anomaly Detection Jing Gao 1, Wei Fan 2, Deepak Turaga 2,
Ensemble Methods in Machine Learning
Classification Ensemble Methods 1
Regress-itation Feb. 5, Outline Linear regression – Regression: predicting a continuous value Logistic regression – Classification: predicting a.
Xiangnan Kong,Philip S. Yu An Ensemble-based Approach to Fast Classification of Multi-label Data Streams Dept. of Computer Science University of Illinois.
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
Combining multiple learners Usman Roshan. Decision tree From Alpaydin, 2010.
1 Systematic Data Selection to Mine Concept-Drifting Data Streams Wei Fan Proceedings of the 2004 ACM SIGKDD international conference on Knowledge discovery.
Mining Concept-Drifting Data Streams Using Ensemble Classifiers Haixun Wang Wei Fan Philip S. YU Jiawei Han Proc. 9 th ACM SIGKDD Internal Conf. Knowledge.
Ensemble Classifiers.
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Machine Learning: Ensemble Methods
Chapter 7. Classification and Prediction
Introduction to Data Mining, 2nd Edition
Where did we stop? The Bayes decision rule guarantees an optimal classification… … But it requires the knowledge of P(ci|x) (or p(x|ci) and P(ci)) We.
Additional notes on random variables
Knowledge Transfer via Multiple Model Local Structure Mapping
Additional notes on random variables
Evolutionary Ensembles with Negative Correlation Learning
Outlines Introduction & Objectives Methodology & Workflow
Presentation transcript:

On Appropriate Assumptions to Mine Data Streams: Analyses and Solutions Jing Gao† Wei Fan‡ Jiawei Han† †University of Illinois at Urbana-Champaign ‡IBM T. J. Watson Research Center

Introduction (1) Data Stream –Continuously arriving data flow –Applications: network traffic, credit card transaction flow, phone calling records, etc

Introduction (2) Stream Classification –Construct a classification model based on past records –Use the model to predict labels for new data –Help decision making Fraud? Fraud Classification model Labeling

Framework ……… ? Classification Model Predict

Existing Stream Mining Methods How to use old examples? –Throw away or fade out old examples –Select old examples or models which match the current concepts How to update the model? –Real Time Update –Batch Update Match the training distribution!

Existing Stream Mining Methods Shared distribution assumption –Training and test data are from the same distribution P(x,y) x-feature vector, y-class label –Validity of existing work relies on the shared distribution assumption Difference from traditional learning –Both distributions evolve ……… training ……… test ……… ……

Appropriateness of Shared Distribution An example of stream data –KDDCUP’99 Intrusion Detection Data –P(y) evolves Shift or delay inevitable –The future data could be different from current data –Matching the current distribution to fit the future one is a wrong way –The shared distribution assumption is inappropriate

Appropriateness of Shared Distribution Changes in P(y) –P(y) P(x,y)=P(y|x)P(x) –The change in P(y) is attributed to changes in P(y|x) and P(x) Time Stamp 1 Time Stamp 11 Time Stamp 21

Realistic and relaxed assumption The training and test distributions are similar to the degree that the model trained from the training set D has higher accuracy on the test set T than both random guessing and predicting the same class label. Training set Test set Model Random Guessing Fixed Guessing

Realistic and relaxed assumption Strengths of this assumption –Does not assume any exact relationship between training and test distribution –Simply assume that learning is useful Develop algorithms based on this assumption –Maximize the chance for models to succeed on future data instead of match current data

A Robust and Extensible Stream Mining Framework C1C1 C2C2 CkCk …… Training set Test set Simple Voting(SV)Averaging Probability(AP)

Why ensemble? Ensemble –Reduce variance caused by single models –Is more robust than single models when the distribution is evolving Expected error analysis –Single model: –Ensemble:

Why simple averaging? Combining outputs –Simple averaging: uniform weights w i =1/k –Weighted ensemble: non-uniform weights w i is inversely proportional to the training errors –w i should reflect P(M), the probability of model M after observing the data Uniform weights are the best –P(M) is changing and we could never estimate the true P(M) and when and how it changes –Uniform weights could minimize the expected distance between P(M) and weight vector

An illustration Single models (M1, M2, M3) have huge variance. Simple averaging ensemble (AP) is more stable and accurate. Weighted ensemble (WE) is not as good as AP since training errors and test errors may have different distributions. Average Probability Weighted Ensemble Single Models

Experiments Set up –Data streams with chunks T 1, T 2, …, T N –Use T i as the training set to classify T i+1 Measures –Mean Squared Error, Accuracy –Number of Wins, Number of Loses –Normalized Accuracy, MSE

Experiments Methods –Single models: Decision tree (DT), SVM, Logistic Regression (LR) –Weighted ensemble: weights reflect the accuracy on training set (WE) –Simple ensemble: voting (SV) or probability averaging (AP)

Experimental Results (1) Comparison on Synthetic Data Time 40 Time 100

Experimental Results (2) Comparison on Intrusion Data Set

Experimental Results (3) Classification Accuracy Comparison

Experimental Results (4) Mean Squared Error Comparison

Conclusions Realistic assumption –Take into account the difference between training and test distributions –Overly matching the training distribution is thus unsatisfactory Model averaging –Robust and accurate –Theoretically proved the effectiveness –Could give the best predictions on average

Thanks! Any questions?