Graph Classification SEG 5010 Week 3.

Slides:



Advertisements
Similar presentations
An Introduction to Artificial Intelligence
Advertisements

gSpan: Graph-based substructure pattern mining
www.brainybetty.com1 MAVisto A tool for the exploration of network motifs By Guo Chuan & Shi Jiayi.
Branch and Bound Example. Initial lower bound Jrpd Use 1 machine preemptive schedule as lower bound Job 2 has a lateness of 5,
Query Optimization of Frequent Itemset Mining on Multiple Databases Mining on Multiple Databases David Fuhry Department of Computer Science Kent State.
CMPUT 466/551 Principal Source: CMU
1 Efficient Subgraph Search over Large Uncertain Graphs Ye Yuan 1, Guoren Wang 1, Haixun Wang 2, Lei Chen 3 1. Northeastern University, China 2. Microsoft.
Boosting CMPUT 615 Boosting Idea We have a weak classifier, i.e., it’s error rate is a little bit better than 0.5. Boosting combines a lot of such weak.
COM (Co-Occurrence Miner): Graph Classification Based on Pattern Co-occurrence Ning Jin, Calvin Young, Wei Wang University of North Carolina at Chapel.
© 2008 IBM Corporation Mining Significant Graph Patterns by Leap Search Xifeng Yan (IBM T. J. Watson) Hong Cheng, Jiawei Han (UIUC) Philip S. Yu (UIC)
Min-Max Trees Based on slides by: Rob Powers Ian Gent Yishay Mansour.
Data Mining Association Analysis: Basic Concepts and Algorithms
SubSea: An Efficient Heuristic Algorithm for Subgraph Isomorphism Vladimir Lipets Ben-Gurion University of the Negev Joint work with Prof. Ehud Gudes.
1 Efficiently Mining Frequent Trees in a Forest Mohammed J. Zaki.
Latent Boosting for Action Recognition Zhi Feng Huang et al. BMVC Jeany Son.
Slides are modified from Jiawei Han & Micheline Kamber
Subgraph Containment Search Dayu Yuan The Pennsylvania State University 1© Dayu Yuan9/7/2015.
Issues with Data Mining
Topological Summaries: Using Graphs for Chemical Searching and Mining Graphs are a flexible & unifying model Scalable similarity searches through novel.
Data mining and machine learning A brief introduction.
Branch & Bound UPPER =  LOWER = 0.
Xiangnan Kong,Philip S. Yu Department of Computer Science University of Illinois at Chicago KDD 2010.
Graph Indexing: A Frequent Structure- based Approach Alicia Cosenza November 26 th, 2007.
Combining multiple learners Usman Roshan. Bagging Randomly sample training data Determine classifier C i on sampled data Goto step 1 and repeat m times.
Xiangnan Kong,Philip S. Yu Multi-Label Feature Selection for Graph Classification Department of Computer Science University of Illinois at Chicago.
Multi-Relational Data Mining: An Introduction Joe Paulowskey.
Tony Jebara, Columbia University Advanced Machine Learning & Perception Instructor: Tony Jebara.
1 Data Mining Functionalities / Data Mining Tasks Concepts/Class Description Concepts/Class Description Association Association Classification Classification.
Summary „Data mining” Vietnam national university in Hanoi, College of technology, Feb.2006.
Summary „Rough sets and Data mining” Vietnam national university in Hanoi, College of technology, Feb.2006.
MAXIMALLY INFORMATIVE K-ITEMSETS. Motivation  Subgroup Discovery typically produces very many patterns with high levels of redundancy  Grammatically.
Discriminative Frequent Pattern Analysis for Effective Classification By Hong Cheng, Xifeng Yan, Jiawei Han, Chih- Wei Hsu Presented by Mary Biddle.
Advanced Gene Selection Algorithms Designed for Microarray Datasets Limitation of current feature selection methods: –Ignores gene/gene interaction: single.
DECISION TREES Asher Moody, CS 157B. Overview  Definition  Motivation  Algorithms  ID3  Example  Entropy  Information Gain  Applications  Conclusion.
Spanning Trees Dijkstra (Unit 10) SOL: DM.2 Classwork worksheet Homework (day 70) Worksheet Quiz next block.
1 Substructure Similarity Search in Graph Databases R 陳芃安.
Ning Jin, Wei Wang ICDE 2011 LTS: Discriminative Subgraph Mining by Learning from Search History.
Search: Games & Adversarial Search Artificial Intelligence CMSC January 28, 2003.
Queensland University of Technology
Finding Dense and Connected Subgraphs in Dual Networks
Area of a Region Between Two Curves (7.1)
Algorithmic Transparency with Quantitative Input Influence
Optimal Algorithms Search and Sort.
Jiawei Han Department of Computer Science
Types of Algorithms.
Introduction to Data Mining, 2nd Edition by
Introduction to Data Mining, 2nd Edition by
Chao Zhang1, Yu Zheng2, Xiuli Ma3, Jiawei Han1
CIKM Competition 2014 Second Place Solution
Transactional data Algorithm Applications
Area of a Region Between Two Curves (7.1)
Mining Frequent Subgraphs
Introduction to Data Mining, 2nd Edition
The Combination of Supervised and Unsupervised Approach
Branch and Bound.
Predicting Student Performance: An Application of Data Mining Methods with an Educational Web-based System FIE 2003, Boulder, Nov 2003 Behrouz Minaei-Bidgoli,
MURI Kickoff Meeting Randolph L. Moses November, 2008
Kevin Mason Michael Suggs
Discriminative Pattern Mining
CS 584 Lecture7 Assignment -- Due Now! Paper Review is due next week.
Statistical Learning Dong Liu Dept. EEIS, USTC.
Machine Learning in Practice Lecture 17
Biological Classification: How would you group these animals?
Branch and Bound Example
Data Mining Classification: Alternative Techniques
Based on slides by: Rob Powers Ian Gent
A task of induction to find patterns
Games & Adversarial Search
Chapter 6— Case Law Analysis
Direct Methods.
Presentation transcript:

Graph Classification SEG 5010 Week 3

A Summary of Graph Features Fingerprint Maccs keys Tree and cyclic patterns Frequent subgraphs Graph fragments

A Boosting Approach to Graph Classification (NIPS04) Apply boosting to graph classification Weak learner: decision stump Definition of the gain function Learning the best weak learner  mining the optimal subgraph An upper bound of the gain function and branch-and-bound search

Leap Search (SIGMOD08) The first study to mine the optimal subgraph given “general” user-specified objective functions Vertical pruning: branch-and-bound An objective function may not be anti-monotone, but its upper bound could be anti-monotone Horizontal pruning: structural proximity If two sibling branches are similar in structure, they may be similar in objective function scores There is a lot of redundancy in the graph pattern search tree

COM (CIKM09) Pattern co-occurrences: for effectiveness Joint discriminative power of multiple graph patterns Individual subgraphs are not discriminative, but their co-occurrences become discriminative A different pattern exploration order: for efficiency Complementary discriminative patterns are examined first Generate patterns with higher scores before those with lower scores Rule-based classifiers: a greedy generation process