Advances in Knowledge Discovery and Data Mining 17th Pacific-Asia Conference, PAKDD 2013, Gold Coast, Australia, April 14-17, 2013, Proceedings, Part I

The two-volume set LNAI 7818 + LNAI 7819 constitutes the refereed proceedings of the 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2013, held in Gold Coast, Australia, in April 2013. The total of 98 papers presented in these proceedings was carefully reviewed and selected from 363 submissions. They cover the general fields of data mining and KDD extensively, including pattern mining, classification, graph mining, applications, machine learning, feature selection and dimensionality reduction, multiple information sources mining, social networks, clustering, text mining, text classification, imbalanced data, privacy-preserving data mining, recommendation, multimedia data mining, stream data mining, data preprocessing and representation.

Discovering Local Subgroups, with an Application to Fraud Detection.- PUF-Tree: A Compact Tree Structure for Frequent Pattern Mining of Uncertain Data.- Frequent Pattern Mining in Attributed Trees.- Mining Frequent Patterns from Human Interactions in Meetings Using Directed Acyclic Graphs.- ClaSP: An Efficient Algorithm for Mining Frequent Closed Sequences.- Efficient Mining of Contrast Patterns on Large Scale Imbalanced Real-Life Data.- Online Cross-Lingual PLSI for Evolutionary Theme Patterns Analysis.- F-Trail: Finding Patterns in Taxi Trajectories.- Mining Appliance Usage Patterns in Smart Home Environment.- Computational Models of Stress in Reading Using Physiological and Physical Sensor Data.- Latent Patient Profile Modelling and Applications with Mixed-Variate Restricted Boltzmann Machine.- MassBayes: A New Generative Classifier with Multi-dimensional Likelihood Estimation.- Fast and Effective Single Pass Bayesian Learning.- Sparse Reductions for Fixed-Size Least Squares Support Vector Machines on Large Scale Data.- Discovery of Regional Co-location Patterns with k-Nearest Neighbor Graph.- Spectral Decomposition for Optimal Graph Index Prediction.- Patterns amongst Competing Task Frequencies: Super-Linearities, and the Almond-DG Model.- Node Classification in Social Network via a Factor Graph Model.- Fast Graph Stream Classification Using Discriminative Clique Hashing.- Mining Interesting Itemsets in Graph Datasets.- Robust Synchronization-Based Graph Clustering.- Efficient Mining of Combined Subspace and Subgraph Clusters in Graphs with Feature Vectors.- Exploiting Temporal Information in a Two-Stage Classification Framework for Content-Based Depression Detection.- EEG-Based Person Verification Using Multi-Sphere SVDD and UBM.- Measuring Reproducibility of High-Throughput Deep-Sequencing Experiments Based on Self-adaptive Mixture Copula.- Mining Representative Movement Patterns through Compression.- NARGES: Prediction Model for Informed Routing in a Communications Network.- Mining Usage Traces of Mobile Apps for Dynamic Preference Prediction.- Leveraging Hybrid Citation Context for Impact Summarization.- Optimal Allocation of High Dimensional Assets through Canonical Vines.- Inducing Context Gazetteers from Encyclopedic Databases for Named Entity Recognition.- An Optimization Method for Proportionally Diversifying Search Results.- Joint Naive Bayes and LDA for Unsupervised Sentiment Analysis.- An Unsupervised Learning Model to Perform Side Channel Attack.- Decisive Supervised Learning.- Learning Overlap Optimization for Domain Decomposition Methods.- CLUEKR : CLUstering Based Efficient kNN Regression.- AREM: A Novel Associative Regression Model Based on EM Algorithm.- One-Class Transfer Learning with Uncertain Data.- Time Series Forecasting Using Distribution Enhanced Linear Regression.- Twin Bridge Transfer Learning for Sparse Collaborative Filtering.- Dimensionality Reduction with Dimension Selection.- Multi-View Visual Classification via a Mixed-Norm Regularizer.- Mining Specific Features for Acquiring User Information Needs.- Ensemble-Based Wrapper Methods for Feature Selection and Class Imbalance Learning.- Exploring Groups from Heterogeneous Data via Sparse Learning.- Multiplex Topic Models.- Integrating Clustering and Ranking on Hybrid Heterogeneous Information Network.- Learning from Multiple Observers with Unknown Expertise.