Program

The Discovery Science 2016 conference will start on October 19th (Wednesday), in the morning and it will end with on October 21st (Friday) in the afternoon.

Proceedings

Discovery Science 2016 proceedings will be freely available from October 10th, 2016 till November 10th, 2016 at the following link: http://link.springer.com/book/10.1007/978-3-319-46307-0

Full Program 

Download here the PDF version of the Discovery Science 2016 program, jointed with Algorithmic Learning Theory 2016.

Discovery Science 2016 Detailed Program

 

Tuesday, 18. October

18:00 – 20:00

Registration Desk

19:00 – 21:00

Welcome Reception at Nicolaus Sheraton Hotel (Roof)

 

Wednesday, 19. October
8:00 – 18:00 Registration Desk
8:50 – 9:00 Conference opening: Donato Malerba, Ronald Ortner, Hans Ulrich Simon, Toon Calders, Michelangelo Ceci
9:00 – 10:30 Tutorial ALT Gábor Lugosi
How to Estimate the Mean of a Random Variable? (Chair: Ronald Ortner)
10:30 – 11:00 Coffee Break and Poster Exhibition
11:00 – 12:40 SESSION 1: Pattern mining and rules – 1h40

(Chair: Nada Lavrac)

11:00 – 11:20

Cláudio Rebelo De Sá, Wouter Duivesteijn, Carlos Soares and Arno Knobbe
Exceptional Preferences Mining

11:20 – 11:40

Guillaume Bosc, Jérôme Golebiowski, Moustafa Bensafi, Céline Robardet, Marc Plantevit, Jean-Francois Boulicaut and Mehdi Kaytoue
Local subgroup discovery for eliciting and understanding new structure-odor relationships

11:40 – 12:00

Matej Mihelčić and Tomislav Šmuc
InterSet: Interactive redescription set exploration

12:00 – 12:20

Matthijs van Leeuwen and Antti Ukkonen
Expect the unexpected – On the significance of subgroups

12:20 – 12:40

Pascal Welke, Tamas Horvath and Stefan Wrobel
Min-Hashing for Probabilistic Frequent Subtree Feature Spaces
12:40 – 14:00 Lunch (Hotel Nicolaus Sheraton)
14:00 – 15:00 Invited Talk ALT/DS John Shawe-Taylor
Margin Based Structured Output Learning (Chair: Donato Malerba)
15:00 – 15:30 Coffee Break and Poster Exhibition
15:30 – 16:45 SESSION 2: Structured output prediction – 1h15’

(Chair: Dragi Kocev)

15:30 – 15:50

Leon Bornemann, Jason Lecerf and Panagiotis Papapetrou
STIFE: A Framework for Feature-based Classification of Sequences of Temporal Intervals

15:50 – 16:10

Giuseppe Rizzo, Claudia d’Amato, Nicola Fanizzi and Floriana Esposito
Approximating Numeric Role Fillers via Predictive Clustering Trees for Knowledge Base Enrichment in the Web of Data

16:10 – 16:30

Aljaz Osojnik, Saso Dzeroski and Dragi Kocev
Option predictive clustering trees for multi-target regression

16:30 – 16:45

Leandro R. Galvão and Luiz Merschmann
HSIM: A Supervised Imputation Method for Hierarchical Classification Scenario
17:00 – 18:00 Business Meeting
18:00 – 19:00 Steering Committee Meeting
19:00 – 20:00 Poster Exhibition (cont.)

 

Thursday, 20. October
8:00 – 18:00 Registration Desk
9:00 – 10:00 Invited Talk ALT Avrim Blum
Learning about Agents and Mechanisms from Opaque Transactions (Chair: Hans U. Simon)
10:00 – 10:30 E. M. Gold Award Talk: Nader Bshouty and Areej Costa
Exact Learning Juntas from Membership Queries (Chair: Sandra Zilles)
10:30 – 11:00 Coffee Break and Poster Exhibition
11:00 – 12:30 SESSION 3: Applications – 1h30

(Chair: Herna Viktor)

11:00 – 11:20

Sebastian Kauschke, Johannes Fürnkranz and Frederik Janssen
Predicting Cargo Train Failures: A Machine Learning Approach for a Lightweight Prototype

11:20 – 11:40

Pasquale Ardimento, Massimo Bilancia and Stefano Monopoli
Predicting bug-fix time: using standard versus topic-based text categorization techniques

11:40 – 11:55

Mariana R. Oliveira, Luís Torgo and Vítor Santos Costa
Predicting Wildfires: Propositional and Relational Spatio-Temporal Pre-Processing Approaches

11:55 – 12:10

Juan Colonna, João Gama and Eduardo Nakamura
Recognizing family, gender and species of anuran using a hierarchical classification approach

12:10 – 12:30

Shazia Tabassum and Joao Gama
Evolution Analysis of Call Ego-Networks
12:30 – 14:00 Lunch (Hotel Nicolaus Sheraton)
14:00 – 15:30 Tutorial DS Gianluca Bontempi
Perspectives of feature selection in bioinformatics: from relevance to causal inference (Chair: Toon Calders)
15:30 – 16:10 SESSION 4: Ensemble Learning – 0h40

(Chair: Johannes Fuernkranz)

15:30 – 15:50

Dariusz Brzezinski and Jerzy Stefanowski
Ensemble Diversity in Evolving Data Streams

15:50 – 16:10

Nikola Simidjievski, Ljupčo Todorovski and Sašo Džeroski
Learning Ensembles of Process-Based Models by Bagging of Random Library Samples
16:20 – Departure to Trani (Cathedral, Castle and walk)
20:00 – 22:00 Conference Dinner (Trani)

 

Friday, 21. October
8:30 – 12:30 Registration Desk
9:00 – 10:00 Invited Talk DS Kristian Kersting
Collective attention on the web (Chair: Michelangelo Ceci)
10:00 – 10:30 Carl H. Smith Award Talk: Isak Karlsson, Panagiotis Papapetrou and Henrik Boström
Early Random Shapelet Forest (Chair: Sašo Džeroski)
10:30 – 11:00 Coffee Break and Poster Exhibition
11:00 – 12:30 SESSION 5: Classification – 1h40

(Chair: João Gama)

11:00 – 11:20

Julius Stecher, Frederik Janssen and Johannes Fürnkranz
Shorter Rules Are Better, Aren’t They?

11:20 – 11:40

Annalisa Appice and Pietro Guccione
Exploiting Spatial Correlation of Spectral Signature for Training Data Selection in Hyperspectral Image Classification

11:40 – 12:00

Matej Petković, Pance Panov and Saso Dzeroski
A Comparison of Different Data Transformation Approaches in the Feature Ranking Context

12:00 – 12:20

Gert Jacobusse and Cor Veenman
On Selection Bias with Imbalanced Classes

12:20 – 12:40

Ali Pesaranghader, Herna Viktor and Eric Paquet
A Framework for Classification in Data Streams using Multi-strategy Learning
12:40 – 14:00 Lunch (Hotel Nicolaus Sheraton)
14:00 – 15:15 SESSION 6: Networks – 1h15’

(Chair: Annalisa Appice)

14:00 – 14:20

Fabrizio Angiulli, Fabio Fassetti and Estela Narvaez
Anomaly Detection in Networks with Temporal Information

14:20 – 14:40

Kouzou Ohara, Kazumi Saito, Masahiro Kimura and Hiroshi Motoda
Accelerating computation of distance based centrality measures for spatial networks

14:40 – 15:00

Ruggero G. Pensa and Gianpiero Di Blasi
A Semi-supervised Approach to Measuring User Privacy in Online Social Networks

15:00 – 15:15

Fabiola Pereira, Sandra de Amo and João Gama
On Using Temporal Networks to Analyze User Preferences Dynamics
15:15 – 15:45 Coffee Break and Poster Exhibition
15:45 – 17:00 SESSION 7: Kernels and deep learning – 1h15’

(Chair: Matthijs van Leeuwen)

15:45 – 16:05

Huibin Shen, Sandor Szedmak, Céline Brouard and Juho Rousu
Soft Kernel Target Alignment for Two-stage Multiple Kernel Learning

16:05 – 16:25

Timo Nolle, Alexander Seeliger and Max Mühlhäuser
Unsupervised Anomaly Detection in Noisy Business Process Event Logs Using Denoising Autoencoders

16:25 – 16:45

Jan Ruben Zilke, Eneldo Loza Mencía and Frederik Janssen
DeepRED – Rule Extraction from Deep Neural Networks

16:45 – 16:55

Katrin Ullrich, Jennifer Mack and Pascal Welke
Ligand Affinity Prediction with Multi-Pattern Kernels
17:00 Closing