Machine Learning and Knowledge Discovery in Databases. Research Track

1. Front Matter

   Pages i-xli

   PDF

2. Online Learning

   1. Front Matter

      Pages 1-1

      PDF

   2. Routine Bandits: Minimizing Regret on Recurring Problems

      • Hassan Saber, Léo Saci, Odalric-Ambrym Maillard, Audrey Durand

      Pages 3-18

   3. Conservative Online Convex Optimization

      • Martino Bernasconi de Luca, Edoardo Vittori, Francesco Trovò, Marcello Restelli

      Pages 19-34

   4. Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits

      • Kaushik Roy, Qi Zhang, Manas Gaur, Amit Sheth

      Pages 35-50

   5. Exploiting History Data for Nonstationary Multi-armed Bandit

      • Gerlando Re, Fabio Chiusano, Francesco Trovò, Diego Carrera, Giacomo Boracchi, Marcello Restelli

      Pages 51-66

   6. High-Probability Kernel Alignment Regret Bounds for Online Kernel Selection

      • Shizhong Liao, Junfan Li

      Pages 67-83

3. Reinforcement Learning

   1. Front Matter

      Pages 85-85

      PDF

   2. Periodic Intra-ensemble Knowledge Distillation for Reinforcement Learning

      • Zhang-Wei Hong, Prabhat Nagarajan, Guilherme Maeda

      Pages 87-103

   3. Learning to Build High-Fidelity and Robust Environment Models

      • Weinan Zhang, Zhengyu Yang, Jian Shen, Minghuan Liu, Yimin Huang, Xing Zhang et al.

      Pages 104-121

   4. Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning

      • Muhammad Rizki Maulana, Wee Sun Lee

      Pages 122-138

   5. Multi-agent Imitation Learning with Copulas

      • Hongwei Wang, Lantao Yu, Zhangjie Cao, Stefano Ermon

      Pages 139-156

   6. CMIX: Deep Multi-agent Reinforcement Learning with Peak and Average Constraints

      • Chenyi Liu, Nan Geng, Vaneet Aggarwal, Tian Lan, Yuan Yang, Mingwei Xu

      Pages 157-173

   7. Model-Based Offline Policy Optimization with Distribution Correcting Regularization

      • Jian Shen, Mingcheng Chen, Zhicheng Zhang, Zhengyu Yang, Weinan Zhang, Yong Yu

      Pages 174-189

   8. Disagreement Options: Task Adaptation Through Temporally Extended Actions

      • Matthias Hutsebaut-Buysse, Tom De Schepper, Kevin Mets, Steven Latré

      Pages 190-205

   9. Deep Adaptive Multi-intention Inverse Reinforcement Learning

      • Ariyan Bighashdel, Panagiotis Meletis, Pavol Jancura, Gijs Dubbelman

      Pages 206-221

   10. Unsupervised Task Clustering for Multi-task Reinforcement Learning

       • Johannes Ackermann, Oliver Richter, Roger Wattenhofer

       Pages 222-237

   11. Deep Model Compression via Two-Stage Deep Reinforcement Learning

       • Huixin Zhan, Wei-Ming Lin, Yongcan Cao

       Pages 238-254

   12. Dropout’s Dream Land: Generalization from Learned Simulators to Reality

       • Zac Wellmer, James T. Kwok

       Pages 255-270

   13. Goal Modelling for Deep Reinforcement Learning Agents

       • Jonathan Leung, Zhiqi Shen, Zhiwei Zeng, Chunyan Miao

       Pages 271-286

The multi-volume set LNAI 12975 until 12979 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2021, which was held during September 13-17, 2021. The conference was originally planned to take place in Bilbao, Spain, but changed to an online event due to the COVID-19 pandemic. 

The 210 full papers presented in these proceedings were carefully reviewed and selected from a total of 869 submissions.

The volumes are organized in topical sections as follows:

Research Track:

Part I: Online learning; reinforcement learning; time series, streams, and sequence models; transfer and multi-task learning; semi-supervised and few-shot learning; learning algorithms and applications.

Part II: Generative models; algorithms and learning theory; graphs and networks; interpretation, explainability, transparency, safety.

Part III: Generative models; search and optimization; supervised learning; text mining and natural language processing; image processing, computer vision and visual analytics.

Applied Data Science Track:

Part IV: Anomaly detection and malware; spatio-temporal data; e-commerce and finance; healthcare and medical applications (including Covid); mobility and transportation.

Part V: Automating machine learning, optimization, and feature engineering; machine learning based simulations and knowledge discovery; recommender systems and behavior modeling; natural language processing; remote sensing, image and video processing; social media.

• applied computing
• artificial intelligence
• communication systems
• computer graphics
• computer networks
• computer systems
• computer vision
• data mining
• education
• image processing
• knowledge representation and reasoning
• law, social and behavioral sciences
• machine learning
• multivariate statisctics
• network protocols
• neural networks
• probability and statistics
• signal processing
• wireless telecommunication systems

• ELLIS - The European Laboratory for Learning and Intelligent Systems, Alicante, Spain

  Nuria Oliver

• ETHZ and EPFL, Zürich, Switzerland

  Fernando Pérez-Cruz

• Johannes Gutenberg University of Mainz, Mainz, Germany

  Stefan Kramer

• École Polytechnique, Palaiseau, France

  Jesse Read

• Basque Center for Applied Mathematics, Bilbao, Spain

  Jose A. Lozano

Policies and ethics