Regular Papers -- Decomposition Algorithms for Training Large-Scale Semiparametric Support Vector Machines -- A Convex Method for Locating Regions of Interest with Multi-instance Learning -- Active Learning for Reward Estimation in Inverse Reinforcement Learning -- Simulated Iterative Classification A New Learning Procedure for Graph Labeling -- Graph-Based Discrete Differential Geometry for Critical Instance Filtering -- Integrating Novel Class Detection with Classification for Concept-Drifting Data Streams -- Neural Networks for State Evaluation in General Game Playing -- Learning to Disambiguate Search Queries from Short Sessions -- Dynamic Factor Graphs for Time Series Modeling -- On Feature Selection, Bias-Variance, and Bagging -- Efficient Pruning Schemes for Distance-Based Outlier Detection -- The Sensitivity of Latent Dirichlet Allocation for Information Retrieval -- Efficient Decoding of Ternary Error-Correcting Output Codes for Multiclass Classification -- The Model of Most Informative Patterns and Its Application to Knowledge Extraction from Graph Databases -- On Discriminative Parameter Learning of Bayesian Network Classifiers -- Mining Spatial Co-location Patterns with Dynamic Neighborhood Constraint -- Classifier Chains for Multi-label Classification -- Dependency Tree Kernels for Relation Extraction from Natural Language Text -- Statistical Relational Learning with Formal Ontologies -- Boosting Active Learning to Optimality: A Tractable Monte-Carlo, Billiard-Based Algorithm -- Capacity Control for Partially Ordered Feature Sets -- Reconstructing Data Perturbed by Random Projections When the Mixing Matrix Is Known -- Identifying the Original Contribution of a Document via Language Modeling -- Relaxed Transfer of Different Classes via Spectral Partition -- Mining Databases to Mine Queries Faster -- MACs: Multi-Attribute Co-clusters with High Correlation Information -- Bi-directional Joint Inference for Entity Resolution and Segmentation Using Imperatively-Defined Factor Graphs.-Latent Dirichlet Allocation for Automatic Document Categorization -- New Regularized Algorithms for Transductive Learning -- Enhancing the Performance of Centroid Classifier by ECOC and Model Refinement -- Optimal Online Learning Procedures for Model-Free Policy Evaluation -- Kernels for Periodic Time Series Arising in Astronomy -- K-Subspace Clustering -- Latent Dirichlet Bayesian Co-Clustering -- Variational Graph Embedding for Globally and Locally Consistent Feature Extraction -- Protein Identification from Tandem Mass Spectra with Probabilistic Language Modeling -- Causality Discovery with Additive Disturbances: An Information-Theoretical Perspective -- Subspace Regularization: A New Semi-supervised Learning Method -- Heteroscedastic Probabilistic Linear Discriminant Analysis with Semi-supervised Extension -- Semi-Supervised Multi-Task Regression -- A Flexible and Efficient Algorithm for Regularized Fisher Discriminant Analysis -- Debt Detection in Social Security by Sequence Classification Using Both Positive and Negative Patterns -- Learning the Difference between Partially Observable Dynamical Systems -- Universal Learning over Related Distributions and Adaptive Graph Transduction -- The Feature Importance Ranking Measure -- Demo Papers -- OTTHO: On the Tip of My THOught -- Protecting Sensitive Topics in Text Documents with PROTEXTOR -- Enhanced Web Page Content Visualization with Firefox -- ClusTR: Exploring Multivariate Cluster Correlations and Topic Trends -- Visual OntoBridge: Semi-automatic Semantic Annotation Software -- Semi-automatic Categorization of Videos on VideoLectures.net -- Discovering Patterns in Flows: A Privacy Preserving Approach with the ACSM Prototype -- Using Temporal Language Models for Document Dating -- Omiotis: A Thesaurus-Based Measure of Text Relatedness -- Found in Translation -- A Community-Based Platform for Machine Learning Experimentation -- TeleComVis: Exploring Temporal Communities in Telecom Networks.

This book constitutes the refereed proceedings of the joint conference on Machine Learning and Knowledge Discovery in Databases: ECML PKDD 2009, held in Bled, Slovenia, in September 2009. The 106 papers presented in two volumes, together with 5 invited talks, were carefully reviewed and selected from 422 paper submissions. In addition to the regular papers the volume contains 14 abstracts of papers appearing in full version in the Machine Learning Journal and the Knowledge Discovery and Databases Journal of Springer. The conference intends to provide an international forum for the discussion of the latest high quality research results in all areas related to machine learning and knowledge discovery in databases. The topics addressed are application of machine learning and data mining methods to real-world problems, particularly exploratory research that describes novel learning and mining tasks and applications requiring non-standard techniques.