1 Zi Yang Tsinghua University Joint work with Prof. Jie Tang, Prof. Juanzi Li, Dr. Keke Cai, Jingyi Guo, Chi Wang, etc. July 21, 2011, CASIN 2011, Tsinghua.

Slides:



Advertisements
Similar presentations
1 Topic Distributions over Links on Web Jie Tang 1, Jing Zhang 1, Jeffrey Xu Yu 2, Zi Yang 1, Keke Cai 3, Rui Ma 3, Li Zhang 3, and Zhong Su 3 1 Tsinghua.
Advertisements

Document Summarization using Conditional Random Fields Dou Shen, Jian-Tao Sun, Hua Li, Qiang Yang, Zheng Chen IJCAI 2007 Hao-Chin Chang Department of Computer.
1 Zi Yang, Wei Li, Jie Tang, and Juanzi Li Knowledge Engineering Group Department of Computer Science and Technology Tsinghua University, China {yangzi,
1 From Sentiment to Emotion Analysis in Social Networks Jie Tang Department of Computer Science and Technology Tsinghua University, China.
Active Learning for Streaming Networked Data Zhilin Yang, Jie Tang, Yutao Zhang Computer Science Department, Tsinghua University.
Influence and Passivity in Social Media Daniel M. Romero, Wojciech Galuba, Sitaram Asur, and Bernardo A. Huberman Social Computing Lab, HP Labs.
Linking Named Entity in Tweets with Knowledge Base via User Interest Modeling Date : 2014/01/22 Author : Wei Shen, Jianyong Wang, Ping Luo, Min Wang Source.
Confluence: Conformity Influence in Large Social Networks
Finding your friends and following them to where you are by Adam Sadilek, Henry Kautz, Jeffrey P. Bigham Presented by Guang Ling 1.
1 Social Influence Analysis in Large-scale Networks Jie Tang 1, Jimeng Sun 2, Chi Wang 1, and Zi Yang 1 1 Dept. of Computer Science and Technology Tsinghua.
1 Yuxiao Dong *$, Jie Tang $, Sen Wu $, Jilei Tian # Nitesh V. Chawla *, Jinghai Rao #, Huanhuan Cao # Link Prediction and Recommendation across Multiple.
Graph Data Management Lab School of Computer Science , Bristol, UK.
1 1 Chenhao Tan, 1 Jie Tang, 2 Jimeng Sun, 3 Quan Lin, 4 Fengjiao Wang 1 Department of Computer Science and Technology, Tsinghua University, China 2 IBM.
Data Mining Techniques Outline
Who Will Follow You Back? Reciprocal Relationship Prediction* 1 John Hopcroft, 2 Tiancheng Lou, 3 Jie Tang 1 Department of Computer Science, Cornell University,
Graphical Models Lei Tang. Review of Graphical Models Directed Graph (DAG, Bayesian Network, Belief Network) Typically used to represent causal relationship.
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.
CS541 Advanced Networking 1 Routing and Shortest Path Algorithms Neil Tang 2/18/2009.
Social Context Based Recommendation Systems and Trust Inference Student: Andrea Manrique ID: ITEC810, Macquarie University1 Advisor: A/Prof. Yan.
Models of Influence in Online Social Networks
Social Network Analysis via Factor Graph Model
1 1 Chenhao Tan, 1 Jie Tang, 2 Jimeng Sun, 3 Quan Lin, 4 Fengjiao Wang 1 Department of Computer Science and Technology, Tsinghua University, China 2 IBM.
Active Learning for Networked Data Based on Non-progressive Diffusion Model Zhilin Yang, Jie Tang, Bin Xu, Chunxiao Xing Dept. of Computer Science and.
1 Zi Yang, Wei Li, Jie Tang, and Juanzi Li Knowledge Engineering Group Department of Computer Science and Technology Tsinghua University, China {yangzi,
Reconstructing Gene Networks Presented by Andrew Darling Based on article  “Research Towards Reconstruction of Gene Networks from Expression Data by Supervised.
Modeling Relationship Strength in Online Social Networks Rongjing Xiang: Purdue University Jennifer Neville: Purdue University Monica Rogati: LinkedIn.
1 From Sentiment to Emotion Analysis in Social Networks Jie Tang Department of Computer Science and Technology Tsinghua University, China.
Advisor-advisee Relationship Mining from Research Publication Network Chi Wang 1, Jiawei Han 1, Yuntao Jia 1, Jie Tang 2, Duo Zhang 1, Yintao Yu 1, Jingyi.
M Machine Learning F# and Accord.net. Alena Dzenisenka Software architect at Luxoft Poland Member of F# Software Foundation Board of Trustees Researcher.
Web Services Flow Language Guoqiang Wang Oct 7, 2002.
Mining Social Network for Personalized Prioritization Language Techonology Institute School of Computer Science Carnegie Mellon University Shinjae.
A Novel Local Patch Framework for Fixing Supervised Learning Models Yilei Wang 1, Bingzheng Wei 2, Jun Yan 2, Yang Hu 2, Zhi-Hong Deng 1, Zheng Chen 2.
Overview of the final test for CSC Overview PART A: 7 easy questions –You should answer 5 of them. If you answer more we will select 5 at random.
Measuring Behavioral Trust in Social Networks
Neural Networks Demystified by Louise Francis Francis Analytics and Actuarial Data Mining, Inc.
1 From Sentiment to Emotion Analysis in Social Networks Jie Tang Department of Computer Science and Technology Tsinghua University, China.
Towards Social User Profiling: Unified and Discriminative Influence Model for Inferring Home Locations Rui Li, Shengjie Wang, Hongbo Deng, Rui Wang, Kevin.
Panther: Fast Top-k Similarity Search in Large Networks JING ZHANG, JIE TANG, CONG MA, HANGHANG TONG, YU JING, AND JUANZI LI Presented by Moumita Chanda.
Observations so far…. In general… There are two ways to design a software system –Centralized control One “driver” function that contains the entire algorithm.
1 CoupledLP: Link Prediction in Coupled Networks Yuxiao Dong #, Jing Zhang +, Jie Tang +, Nitesh V. Chawla #, Bai Wang* # University of Notre Dame + Tsinghua.
Supervised Random Walks: Predicting and Recommending Links in Social Networks Lars Backstrom (Facebook) & Jure Leskovec (Stanford) Proc. of WSDM 2011 Present.
Steffen Staab 1WeST Web Science & Technologies University of Koblenz ▪ Landau, Germany Network Theory and Dynamic Systems Cascading.
Household Members’ Time Allocation to Daily Activities and Decision to Hire Domestic Helpers Donggen WANG and Jiukun LI Department of Geography Hong Kong.
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 Mining Advisor-Advisee Relationships from Research Publication.
Error-Correcting Code
1 Relational Factor Graphs Lin Liao Joint work with Dieter Fox.
Analysis of Massive Data Sets Prof. dr. sc. Siniša Srbljić Doc. dr. sc. Dejan Škvorc Doc. dr. sc. Ante Đerek Faculty of Electrical Engineering and Computing.
Biao Wang 1, Ge Chen 1, Luoyi Fu 1, Li Song 1, Xinbing Wang 1, Xue Liu 2 1 Shanghai Jiao Tong University 2 McGill University
The Inherent Security of Routing Protocols in Ad Hoc and Sensor Networks Tanya Roosta (EECS, Berkeley) In Collaboration With: Sameer Pai (ECE, Cornell)
1 Zi Yang Tsinghua University Joint work with Prof. Jie Tang, Prof. Juanzi Li, Dr. Keke Cai, Jingyi Guo, Chi Wang, etc. July 21, 2011, CASIN 2011, Tsinghua.
Wenyu Zhang From Social Network Group
Hao Ma, Haixuan Yang, Michael R. Lyu and Irwin King CIKM, 2008.
Artificial Intelligence Project
Learning Coordination Classifiers
Cross-lingual Knowledge Linking Across Wiki Knowledge Bases
Factor Graphs and the Sum-Product Algorithm
Estimating Link Signatures with Machine Learning Algorithms
CS223 Advanced Data Structures and Algorithms
Weakly Learning to Match Experts in Online Community
Structural influence:
Binghui Wang, Le Zhang, Neil Zhenqiang Gong
Socialized Word Embeddings
GANG: Detecting Fraudulent Users in OSNs
Actively Learning Ontology Matching via User Interaction
“Traditional” image segmentation
Yingze Wang and Shi-Kuo Chang University of Pittsburgh
Modeling Topic Diffusion in Scientific Collaboration Networks
Presentation transcript:

1 Zi Yang Tsinghua University Joint work with Prof. Jie Tang, Prof. Juanzi Li, Dr. Keke Cai, Jingyi Guo, Chi Wang, etc. July 21, 2011, CASIN 2011, Tsinghua Predictive Models in Social Network Analysis

2 Background Predictive Models –To predict in a formal and systematic way Formulate the predictive objective with a function, and design algorithm for it. Disadvantage: Hard to build objective and derive algorithm. Conventional Build models based on designed parameters and factors. Predict based on belief propagation/sampling-based methods. PGM-based

3 Background Factor graph model –Factor graph A factorized function expressed by a bipartite graph, Node: Parameter node and factor node, Edge: Factor associating parameters. –Factor graph model Belief propagation: message passing along edges.

4 Background Factor graph model –Factor graph A factorized function expressed by a bipartite graph, Node: Parameter node and factor node, Edge: Factor associating parameters. –Factor graph model Belief propagation: message passing along edges. Advantages 1.Easy to formulate complicated objective function. 2.Easy to derive algorithm based on belief propagation. 3.Easy to deploy on parallel or distributed system. Advantages 1.Easy to formulate complicated objective function. 2.Easy to derive algorithm based on belief propagation. 3.Easy to deploy on parallel or distributed system.

5 Outline Predictive Models in Social Network Analysis Example Problems Representative User Finding Message Forwarding Prediction Social Context Summarization preference/relation; unsupervised behavior; supervised IR/NLP; supervised supervision take advantages of conventional textual and social information

6 Representative User Finding Problem Definition Social network In Relationship strength In For user, a representative user Out

7 Representative User Finding Modeling –Edge factor –Regional factor Same representative Different representatives Social homophily Global constraint Avoid “leader without followers”

8 Message Forwarding Prediction Problem Definition Social network In Tweets In

9 Message Forwarding Prediction Problem Definition Social network In Tweets In

10 Message Forwarding Prediction Modeling –Local factor –Path constraint factor Collaborative decision with his/her followers and followees Sum-of- square error

11 Social Context Summarization Problem Definition Social Context Augmented Network In Doc Social Context (tweets and users) Relationships between sentences, users, tweets Important sentences/tweets Out

12 Social Context Summarization Modeling Local factor Dependency factor

13 Social Context Summarization Modeling Local factor Dependency factor Similarity > threshold Similarity > threshold

14 Experiments Data Sets –Arnetminer, Twitter, Digg, News Websites (CNN/BBC/ESPN/MTV), Social Blog (Mashable). Baseline methods –Unsupervised methods, logistic regression, CRF, SVM, etc. Results show improvements over the baseline methods on those applications. –Details are omitted due to time limitation.

15 Thanks a lot! Zi Yang Tsinghua University July 21, 2011, CASIN 2011, Tsinghua