Program

Monday, 10 October

Registration (8h15 - 9h) Amphithéâtre St Priest - Batiment 2

Opening (9h - 9h30)

Invited Speaker: Stefan Kramer (9h30 - 10h30)

Coffee Break (10h30 - 11h)

Session 1: Regression and Limited Data -  (11h - 12h15) - Chair Saso Dzeroski

Model Optimization in Imbalanced Regression - F (pdf)

Discovery of differential equations using probabilistic grammars - S (pdf)

Hyperparameter Importance of Quantum Neural Networks Across Small Datasets - F (pdf)

ImitAL: Training Active Learning by Imitation Learning on pure Synthetic Data - S (pdf)

Lunch Time (12h15 - 13h45)

BEST STUDENT PAPER PRESENTATION (13h45 - 14h15) :

Leveraging spatio-temporal autocorrelation phenomena to improve the forecasting of the energy consumption in smart grids (pdf)

Session 2: Incremental/Continual Learning (14h15 - 16h) - Chair Michelangelo Ceci

Predicting Potential Real-time Donations in YouTube Live Streaming Services via Continuous-time Dynamic Graph - F (pdf)

Semi-supervised change point detection using active learning - F (pdf)

Adaptive Neural Networks for Online Domain Incremental Continual Learning - F (pdf)

Incremental Update of Locally Optimal Classification Rules - S (pdf)

Policy Evaluation with Delayed, Aggregated Anonymous Feedback - S (pdf)

Coffee Break ( 16h - 16h30 )

Session 3: Spatial and temporal analysis - (16h30 - 17h50) - Chair Sabrina Gaito

Spatial cross-validation for globally distributed data - F (pdf)

Elastic Product Quantization for Time Series - F (pdf)

Stress Detection from Wearable Sensor Data using Gramian Angular Fields and CNN - S (pdf)

Multi-attribute Transformers for Sequence Prediction in Business Process Management - S (pdf)

Steering Committee Meeting - (17h50 - 18h50)

Welcome Reception - (18h00 - 20h30)

S: Short paper = 15 minutes (with Q&A)

F: Full paper = 20 minutes (with Q&A)

====== ====== ====== ====== ====== ====== ====== ====== ====== 

Tuesday, 11 October

Invited Speaker:  Luca Maria Aiello (9h - 10h)

Coffee Break (10h - 10h30)

Session 4: Social Media Analysis (10h30 - 12h10) - Chair Andrea Tagarelli

Data-Driven Prediction of Athletes' Performance based on their Social Media Presence - F (pdf)

Link prediction with text in online social networks: the role of textual content on high-resolution temporal data - F (pdf)

Weakly supervised Named Entity Recognition for Carbon Storage using Deep Neural Networks - F (pdf)

Predicting User Dropouts from their Online Learning Behavior - S (pdf)

Efficient Multivariate Data Fusion for Misinformation Detection During High Impact Events - F (pdf)

Lunch Time (12h10 - 13h45)

Session 5: Fairness and Outlier detection (13h45 - 15h25) - Chair Riccardo Guidotti

MQ-OFL: Multi-Sensitive Queue-based Online Fair Learning - F (pdf)

Multi-fairness under class-imbalance - F (pdf)

When Correlation Clustering Meets Fairness Constraints - F (pdf)

Cooperative Deep Unsupervised Anomaly Detection - S (pdf)

On the ranking of variable length discords through a hybrid outlier detection approach - F (pdf)

Coffee Break (15h25 - 15h55)

Session 6: Text, Ontologies and Cross-modal learning ( 15h55 - 17h15 ) - Chair Cheick Tidiane Ba

TextMatcher: Cross-Attentional Neural Network to Compare Image and Text - F (pdf)

Can Cross-domain Term Extraction Benefit from Cross-lingual Transfer? - F (pdf)

Retrieval-efficiency trade-off of Unsupervised Keyword Extraction - F (pdf)

A Fuzzy OWL Ontologies Embedding for Complex Ontology Alignments - S (pdf)

Community Meeting (17h15 - 18h15)

Trip + Gala Dinner (18h30 - 23h)

S: Short paper = 15 minutes (with Q&A)

F: Full paper = 20 minutes (with Q&A)

====== ====== ====== ====== ====== ====== ====== ====== ====== 

Wednesday, 12 October

Invited Speaker:  Leman Akoglu    (9h - 10h)

Coffee Break (10h - 10h30)

Session 7: Optimization and Network analysis ( 10h30 - 12h30 ) - Chair Cassio Fraga Dantas

Optimal Decoding of Hidden Markov Models With Consistency Constraints - S (pdf)

Semi-parametric approach to random forests for high-dimensional Bayesian optimisation - S (pdf)

A Clustering-inspired Quality Measure for Exceptional Preferences Mining - Design Choices and Consequences - F (pdf)

Recurrent segmentation meets block models in temporal networks - F (pdf)

Community detection in edge-labeled graphs - F (pdf)

A Fast Heuristic for Computing Geodesic Closures in Large Networks  - F (pdf)

Lunch Time (12h30 - 13h30) 

Session 8: Explainability and Interpretability ( 13h30 - 15h10 ) - Chair Diego Marcos

JUICE: JUstIfied Counterfactual Explanations - F (pdf)

Explaining Siamese Networks in Few-Shot Learning for Audio Data - F (pdf)

Interpretable Latent Space to Enable Counterfactual Explanations - F (pdf)

Shapley Chains: Extending Shapley values to Classifier Chains - F (pdf)

Explaining Crash Predictions on Multivariate Time Series Data - S (pdf)

Closing ( 15h10 - 15h25 )

S: Short paper = 15 minutes (with Q&A)

F: Full paper = 20 minutes (with Q&A)