Conference schedule
This schedule is final. Last update: 01-10-2007 Detailed schedules of workshops and tutorials are avaliable in "Worskhops" and "Tutorials" sections, respectively.
Schedules at a glance (new window): Discovery Challenge, Tutorials and Workshops on Monday, September 17 Main Conferences, Tuesday, Wednesday, Thursday, September 18-20 Tutorials and Workshops on Friday, September 21 Sunday, 16  |  Monday, 17  |   Tuesday, 18  |  Wednesday, 19  |   Thursday, 20  |  Friday, 21
Sunday, September 16th
16:00-19:00	Pre-conference registration desk. Participants registering on that day will have the opportunity to join guided walk around the campus and neighbouring historic part of the city (Old Town).
Monday, September 17th
9:00-17:20	Workshops and Tutorials * Discovery Challenge, sponsored by Gemius         Workshops: * Data Mining in Functional Genomics and Proteomics: Current Trends    and Future Directions * Knowledge Discovery from Ubiquitous Data Streams * Planning to Learn * Multi-Relational Data Mining * Graph Labelling Workshop and Web Spam Challenge * Approaches and Applications of Inductive Programming * Mining Complex Data - Two-day event, extends to Friday 21st         Tutorials: * State-of-the-Art in Data Stream Mining * Exploring the Power of Links in Data Mining * The Challenges of the Semantic Web to Machine Learning and Data Mining * Discovering and Tracking User Communities
17:30 -	Auditorium - Conference Opening Ceremony
19:00 -	Welcome Reception in Porczyński Gallery
Tuesday, September 18th
9:00-10:00	Auditorium - Invited talk:  Tom M. Mitchell, sponsored by PASCAL Title: Learning, Information Extraction and the Web Session Chair: Dunja Mladenic
10:00-10:40	Auditorium - Award Session - ECML Best Paper presentation, sponsored by KDubiq Session Chair: Stan Matwin 298 - Probabilistic Explanation Based Learning         by Angelika Kimmig, Luc De Raedt, Hannu Toivonen         Parallel sessions:
11:10-12:25	S1: Ensemble Methods - Auditorium Session Chair: Joao Gama 315 - Random k-Labelsets: An Ensemble Method for Multilabel Classification,         by Grigorios Tsoumakas, Ioannis Vlahavas 329 - Seeing the Forest through the Trees: Learning a Comprehensible         Model from an Ensemble,         by Anneleen Van Assche, Hendrik Blockeel 541 - Constraint Selection by Committee: An Ensemble Approach to Identifying         Informative Constraints for Semi-Supervised Clustering,         by Derek Greene, Pádraig Cunningham S2: Structure Learning - Room 111-112-113 Session Chair: Zbigniew W. Ras 247 - Learning Similarity between Tree Structured Data: Application         to Image Recognition,         by Laurent Boyer, Amaury Habrard, Marc Sebban 283 - Structure Learning of Probabilistic Relational Models from Incomplete         Relational Data,         by Xiao-Lin Li, Zhi-Hua Zhou 365 - Efficient Computation of Recursive Principal Component Analysis         for Structured Input,         by Alessandro Sperduti S3: Nearest Neighbor Methods - Room 114-115-116 Session Chair: Igor Kononenko  11 - IKNN: Informative K-Nearest Neighbor Pattern Classification,         by Yang Song, Jian Huang, Ding Zhou, Hongyuan Zha, C. Lee Giles 173 - A Comparison of Two Approaches to Classify with Guaranteed Performance,         by Stijn Vanderlooy, Ida G. Sprinkhuizen-Kuyper 524 - An Empirical Comparison of Exact Nearest Neighbour Algorithms,         by Ashraf Kibriya, Eibe Frank
12:30-14:00	Lunch break
14:00-15:40	S4: Markov Models - Auditorium Session Chair: Luc De Raedt 217 - Efficient Weight Learning for Markov Logic Networks,         by Daniel Lowd, Pedro Domingos 218 - Separating Precision and Mean in Dirichlet-enhanced High-order         Markov Models,         by Rikiya Takahashi 392 - Discriminative Sequence Labeling by Z-score Optimization,         by Elisa Ricci, Tijl de Bie, Nello Cristianini   51 - Learning Partially Observable Markov Models from First Passage Times,         by Jérôme Callut, Pierre Dupont S5: Clustering - Room 111-112-113 Session Chair: Eibe Frank 279 - Context-specific Independence Mixture Modelling for Protein Families,         by Benjamin Georgi, Jörg Schultz, Alexander Schliep 412 - Clustering Trees with Instance Level Constraints,         by Jan Struyf, Sašo Džeroski  49 - A Prediction-based Visual Approach for Cluster Exploration         and Cluster Validation by HOV3,         by Ke-Bing Zhang, Mehmet A. Orgun, Kang Zhang 517 - Spectral Clustering and Embedding with Hidden Markov Models,         by Tony Jebara, Yingbo Song, Kapil Thadani S6: Unlabeled Data/Active Learning - Room 114-115-116 Session Chair: Abolfazl Fazel Famili 157 - Learning Balls of Strings with Correction Queries,         by Leonor Becerra Bonache, Colin de la Higuera, Jean-Christophe Janodet,         Frédéric Tantini 203 - Analyzing Co-Training Style Algorithms,         by Wei Wang, Zhi-Hua Zhou 509 - Dual Strategy Active Learning,         by Pinar Donmez, Jaime G. Carbonell, Paul N. Bennett 481 - Finding Transport Proteins in a General Protein Database,         by Sanmay Das, Milton H. Saier, Charles Elkan
16:10-18:30	Plenary Session - ECML poster highlights - Auditorium Session Chairs: Stan Matwin and Dunja Mladenic Poster session schedule
19:00-22:00	ECML Poster reception at Staszic Palace
Wednesday, September 19th
9:00-10:00	Auditorium - Invited talk:  Ricardo Baeza-Yates, sponsored by PASCAL Title: Mining Queries Session Chair: Stan Matwin
10:00-11:00	Auditorium - Award Session - ECML/PKDD Best Student Papers, sponsored by Machine Learning Session Chair: Joost N. Kok and Dunja Mladenic 527 - Additive Groves of Regression Trees         by Daria Sorokina, Rich Caruana, Mirek Riedewald 531 - Bridged Refinement for Transfer Learning         by Dikan Xing, Wenyuan Dai, Gui-Rong Xue, Yong Yu         Parallel sessions:
11:20-12:35	S7: Data Mining - Auditorium Session Chair: Hendrik Blockeel 131 - Approximating Gaussian Processes with H2-matrices,         by Steffen Börm, Jochen Garcke  16 - Learning to Detect Adverse Traffic Events from Noisily Labeled Data,         by Tomáš Šingliar, Miloš Hauskrecht 255 - Feature Extraction from Sensor Data Streams for Real-Time Human Behaviour         Recognition,         by Julia Hunter, Martin Colley S8: Labeled Data - Room 111-112-113 Session Chair: Rayid Ghani 154 - Level Learning Set: A Novel Classifier Based on Active Contour Models,         by Xiongcai Cai, Arcot Sowmya 164 - Avoiding Boosting Overfitting by Removing ''Confusing Samples'',         by Alexander Vezhnevets, Olga Barinova S9: Statistical Models - Room 114-115-116 Session Chair: Szymon Jaroszewicz 109 - Finding the Right Family: Parent and Child Selection for Averaged         One-Dependence Estimators,         by Fei Zheng, Geoff Webb 114 - Source Separation with Gaussian Process Models,         by Sunho Park, Seungjin Choi 275 - Bayesian Inference for Sparse Generalized Linear Models,         by Matthias Seeger, Sebastian Gerwinn, Matthias Bethge
12:30-14:00	Lunch break
14:00-15:15	S10: Data Mining/Social Networks - Auditorium Session Chair: Filip Železný 444 - Privacy Preserving Market Basket Data Analysis,         by Ling Guo, Songtao Guo, Xintao Wu 539 - Towards data mining without information on knowledge structure,         by Alexandre Vautier, Marie-Odile Cordier, René Quiniou 116 - Generating Social Network Features for Link-based Classification,         by Jun Karamon, Yutaka Matsuo, Hikaru Yamamoto, Mitsuru Ishizuka S11: Labeled Data - Room 111-112-113 Session Chair: Mieczyslaw A. Klopotek 206 - The Cost of Learning Directed Cuts,         by Thomas Gärtner, Gemma C. Garriga 287 - Classification of anti-learnable biological and synthetic data,         by Adam Kowalczyk 396 - Relaxation Labeling for Selecting and Exploiting Efficiently Non-Local         Dependencies in Sequence Labeling,         by Guillaume Wisniewski, Patrick Gallinari S12: Statistical Models/Reinforcement Learning - Room 114-115-116 Session Chair: Toon Calders 348 - Statistical Model for Rough Set Approach to Multicriteria Classification,         by Wojciech Kotłowski, Krzysztof Dembczyński, Salvatore Greco,         Roman Słowiński 505 - Statistical Debugging using Latent Topic Models,         by David Andrzejewski, Anne Mulhern, Ben Liblit, Xiaojin Zhu 331 - Policy Gradient Critics,         by Daan Wierstra, Jürgen Schmidhuber
15:45-17:00	S13: Social Networks/Bayesian Networks - Auditorium Session Chair: Hillol Kargupta 403 - An Algorithm to Find Overlapping Community Structure in Networks,         by Steve Gregory 231 - Bayesian Substructure Learning - Approximate Learning of Very Large         Network Structures,         by Andreas Nägele, Mathäus Dejori, Martin Stetter 374 -  Shrinkage Estimator for Bayesian Network Parameters,         by John Burge, Terran Lane S14: Labeled Data/AUC - Room 111-112-113 Session Chair: Zhi-Hua Zhou 570 - On Pairwise Naive Bayes Classifiers,         by Jan-Nikolas Sulzmann, Johannes Fürnkranz, Eyke Hüllermeier 177 - Hinge Rank Loss and the Area under the ROC Curve,         by Harald Steck 291 - Finding Outlying Items in Sets of Partial Rankings,         by Antti Ukkonen, Heikki Mannila S15: Reinforcement Learning - Room 114-115-116 Session Chair: Alessandro Sperduti 407 - Planning and Learning in Environments with Delayed Feedback,         by Thomas J. Walsh, Ali Nouri, Lihong Li, Michael L. Littman  84 - Safe Q-Learning on Complete History Spaces,         by Stephan Timmer, Martin Riedmiller 445 - Graph-Based Domain Mapping for Transfer Learning in General Games,         by Gregory Kuhlmann, Peter Stone
11:20-17:00	Industrial track - Room 211-212-213
17:10-19:00	Auditorium - Community meeting
19:30 -	Conference Banquet at Zachęta National Gallery
Thursday, September 20th
9:00-10:00	Auditorium - Invited talk:  Peter Flach, sponsored by PASCAL Title: Putting Things in Order: On the Fundamental Role of Ranking in Classification and Probability Estimation Session Chair: Joost N. Kok
10:00-10:40	Auditorium - Award Session - PKDD Best Paper presentation, sponsored by KDubiq Session Chair: Andrzej Skowron 133 - Efficient AUC Optimization for Classification         by Toon Calders, Szymon Jaroszewicz         Parallel sessions:
11:10-12:25	S16: Text Mining - Auditorium Session Chair: Myra Spiliopoulou 166 - Classification of Web Documents Using a Graph-Based Model         and Structural Patterns,         by Andrzej Dominik, Zbigniew Walczak, Jacek Wojciechowski 226 - Learning to Classify Documents with Only a Small Positive Training Set,         by Xiao-Li Li, Bing Liu, See-Kiong Ng 341 - Using the Web to Reduce Data Sparseness in Pattern-based Information         Extraction,         by Sebastian Blohm, Philipp Cimiano S17: Dimensionality Reduction - Room 111-112-113 Session Chair: Adam Kowalczyk 126 - Fast Optimization for L1 Regularization: Evaluation and Two New Approaches,         by Mark Schmidt, Glenn M. Fung, Romer Rosales 361 - A Graphical Model for Content Based Image Suggestion and Feature Selection,         by Sabri Boutemedjet, Djemel Ziou, Nizar Bouguila 440 - Stability based Sparse LSI/PCA: Incorporating Feature Selection         in LSI and PCA,         by Dimitrios Mavroeidis, Michalis Vazirgiannis S18: Model Selection - Room 114-115-11 Session Chair: Roman Słowiński 261 - An Improved Model Selection Heuristic for AUC,         by Shaomin Wu, Peter Flach, Cèsar Ferri 316 - Improved Algorithms for Univariate Discretization of Continuous Features,         by Jussi Kujala, Tapio Elomaa 330 - Experiment Databases: Towards an Improved Experimental Methodology         in Machine Learning,         by Hendrik Blockeel, Joaquin Vanschoren
12:30-14:00	Lunch break
14:00-15:15	S19: Text Mining/Unlabeled Data - Auditorium Session Chair: Xiaoli Li 372 - Site-Independent Template-Block Detection,         by Aleksander Kolcz, Wen-tau Yih 589 - Context Sensitive Paraphrasing with a Single Unsupervised Classifier,         by Michael Connor, Dan Roth 518 - Domain Adaptation of Conditional Probability Models via Feature Subsetting,         by Sandeepkumar Satpal, Sunita Sarawagi S20: Dimensionality Reduction/Reinforcement Learning - Room 111-112-113 Session Chair: Shusaku Tsumoto 483 - Classification in Very High Dimensional Problems with Handfuls of Examples,         by Mark M. Palatucci, Tom M. Mitchell  62 - Speeding up Feature Subset Selection through Mutual Information Relevance         Filtering,         by Gert Van Dijck, Marc M. Van Hulle 469 - Efficient Continuous-Time Reinforcement Learning with Adaptive State Graphs,         by Gerhard Neumann, Michael Pfeiffer, Wolfgang Maass S21: Model Selection/Active Learning - Room 114-115-116 Session Chair: Tony Jebara 496 - Classifier Loss under Metric Uncertainty,         by David Skalak, Alexandru Niculescu-Mizil, Rich Caruana 523 - Neighborhood-Based Local Sensitivity,         by Paul N. Bennett 191 - Decision Tree Instability and Active Learning,         by Kenneth Dwyer, Robert Holte
15:45-18:30	Plenary Session - PKDD poster highlights and EU projects presentation - Auditorium Session Chairs: Joost N. Kok and Andrzej Skowron Poster session schedule
19:00-22:00	PKDD Poster and EU Projects reception at Staszic Palace, sponsored by KDubiq
Friday, September 21st
9:00-10:00	Auditorium - Invited talk:  Barry Smyth, sponsored by PASCAL Title: Adventures in Personalized Information Access Session Chair: Andrzej Skowron
10:30-17:30	Workshops and Tutorials         Workshops: * Prior Conceptual Knowledge in Machine Learning and Knowledge Discovery * Web Mining 2.0 * International Workshop on Constraint-Based Mining and Learning * Rough Sets in Knowledge Discovery: Foundations and Applications * Mining Complex Data - Two day event, starts on Monday 17th         Tutorials: * Mining Large Graphs: Laws and tools * Knowledge Discovery Standards in Ubiquitous Environments * An introduction to Statistical Relational Learning