Skip to main content
  • Conference proceedings
  • © 2023

Machine Learning and Knowledge Discovery in Databases

European Conference, ECML PKDD 2022, Grenoble, France, September 19–23, 2022, Proceedings, Part III

Part of the book series: Lecture Notes in Computer Science (LNCS, volume 13715)

Part of the book sub series: Lecture Notes in Artificial Intelligence (LNAI)

Conference series link(s): ECML PKDD: Joint European Conference on Machine Learning and Knowledge Discovery in Databases

Conference proceedings info: ECML PKDD 2022.

Buy it now

Buying options

eBook USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

This is a preview of subscription content, log in via an institution to check for access.

Table of contents (40 papers)

  1. Front Matter

    Pages i-xlvi
  2. Deep Learning

    1. Front Matter

      Pages 1-1
    2. DialCSP: A Two-Stage Attention-Based Model for Customer Satisfaction Prediction in E-commerce Customer Service

      • Zhenhe Wu, Liangqing Wu, Shuangyong Song, Jiahao Ji, Bo Zou, Zhoujun Li et al.
      Pages 3-18
    3. Foveated Neural Computation

      • Matteo Tiezzi, Simone Marullo, Alessandro Betti, Enrico Meloni, Lapo Faggi, Marco Gori et al.
      Pages 19-35
    4. Class-Incremental Learning via Knowledge Amalgamation

      • Marcus de Carvalho, Mahardhika Pratama, Jie Zhang, Yajuan Sun
      Pages 36-50
    5. Trigger Detection for the sPHENIX Experiment via Bipartite Graph Networks with Set Transformer

      • Tingting Xuan, Giorgian Borca-Tasciuc, Yimin Zhu, Yu Sun, Cameron Dean, Zhaozhong Shi et al.
      Pages 51-67
    6. Understanding Difficulty-Based Sample Weighting with a Universal Difficulty Measure

      • Xiaoling Zhou, Ou Wu, Weiyao Zhu, Ziyang Liang
      Pages 68-84
    7. Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks

      • Ghada Sokar, Decebal Constantin Mocanu, Mykola Pechenizkiy
      Pages 85-101
    8. PrUE: Distilling Knowledge from Sparse Teacher Networks

      • Shaopu Wang, Xiaojun Chen, Mengzhen Kou, Jinqiao Shi
      Pages 102-117
  3. Robust and Adversarial Machine Learning

    1. Front Matter

      Pages 119-119
    2. Fooling Partial Dependence via Data Poisoning

      • Hubert Baniecki, Wojciech Kretowicz, Przemyslaw Biecek
      Pages 121-136Open Access
    3. FROB: Few-Shot ROBust Model for Joint Classification and Out-of-Distribution Detection

      • Nikolaos Dionelis, Sotirios A. Tsaftaris, Mehrdad Yaghoobi
      Pages 137-153
    4. PRoA: A Probabilistic Robustness Assessment Against Functional Perturbations

      • Tianle Zhang, Wenjie Ruan, Jonathan E. Fieldsend
      Pages 154-170
    5. Hypothesis Testing for Class-Conditional Label Noise

      • Rafael Poyiadzi, Weisong Yang, Niall Twomey, Raul Santos-Rodriguez
      Pages 171-186
    6. On the Prediction Instability of Graph Neural Networks

      • Max Klabunde, Florian Lemmerich
      Pages 187-202
    7. Adversarially Robust Decision Tree Relabeling

      • Daniël Vos, Sicco Verwer
      Pages 203-218
    8. Calibrating Distance Metrics Under Uncertainty

      • Wenye Li, Fangchen Yu
      Pages 219-234
    9. Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising

      • Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
      Pages 235-250
    10. Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation

      • Zhihao Zhu, Chenwang Wu, Min Zhou, Hao Liao, Defu Lian, Enhong Chen
      Pages 251-268
    11. Securing Cyber-Physical Systems: Physics-Enhanced Adversarial Learning for Autonomous Platoons

      • Guoxin Sun, Tansu Alpcan, Benjamin I. P. Rubinstein, Seyit Camtepe
      Pages 269-285

About this book

The multi-volume set LNAI 13713 until 13718 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2022, which took place in Grenoble, France, in September 2022.

The 236 full papers presented in these proceedings were carefully reviewed and selected from a total of 1060 submissions. In addition, the proceedings include 17 Demo Track contributions.

The volumes are organized in topical sections as follows:

Part I: Clustering and dimensionality reduction; anomaly detection; interpretability and explainability; ranking and recommender systems; transfer and multitask learning;

Part II: Networks and graphs; knowledge graphs; social network analysis; graph neural networks; natural language processing and text mining; conversational systems;

Part III: Deep learning; robust and adversarial machine learning; generative models; computer vision; meta-learning, neural architecture search;

Part IV: Reinforcement learning; multi-agent reinforcement learning; bandits and online learning; active and semi-supervised learning; private and federated learning; .

Part V: Supervised learning; probabilistic inference; optimal transport; optimization; quantum, hardware; sustainability;

Part VI: Time series; financial machine learning; applications; applications: transportation; demo track.

Editors and Affiliations

  • Grenoble Alpes University, Saint Martin d'Hères, France

    Massih-Reza Amini

  • INSA Rouen Normandy, Saint Etienne du Rouvray, France

    Stéphane Canu

  • Ruhr-Universität Bochum, Bochum, Germany

    Asja Fischer

  • KU Leuven, Leuven, Belgium

    Tias Guns

  • Central European University, Vienna, Austria

    Petra Kralj Novak

  • Aristotle University of Thessaloniki, Thessaloniki, Greece

    Grigorios Tsoumakas

Bibliographic Information

Buy it now

Buying options

eBook USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access