1. Dates
2. Keynote Speakers
3. Call for Papers
4. Schedule
5. Accepted Papers
6. Awards
7. Organizers and PC
8. Previous Workshops

21st International Workshop on Mining and Learning with Graphs

Important Dates

• Paper Submission deadline: 15.06.2024
• Paper acceptance notification: 15.07.2024
• Camera ready submission deadline: 26.08.2024
• Workshop date Monday, 09.09.2024

Keynote Speakers

• 
  Yllka Velaj
  University of Vienna

• Embedding and Clustering of Attributed Multiplex Networks

  Complex information can be represented as networks (graphs) characterized by multiple types of nodes and relationships between them, i.e. multiplex networks. Additionally, these networks are enriched with different types of node features and labels. In this talk, I will present an embedding approach for Attributed Multiplex Networks, to jointly embed nodes and node attributes of multiplex networks in a low dimensional space. The experiments show that the proposed approach outperforms state-of-the-art methods for downstream tasks such as semi-supervised node classification and node clustering.

• 
  Haggai Maron
  Technion & NVIDIA

• Exploiting Symmetries for Learning in Deep Weight Spaces

  This talk explores the emerging research direction that studies neural network weights as a novel data modality. We'll discuss recent advances in processing and analyzing raw weight matrices, which exhibit inherent symmetries reminiscent of other structured data types such as graphs. Our focus will be on designing deep architectures that effectively operate on weight spaces while respecting these symmetries. We'll present our ICML 2023 work on equivariant architectures for processing multilayer perceptron weight spaces, and our ICLR 2024 research on Graph Metanetworks (GMN), which generalizes this approach to diverse network architectures by representing them as graphs. Additionally, we'll touch on our recent ICML 2024 works exploring data augmentations in weight spaces and data-driven network alignment. These developments open new possibilities for deep network analysis, editing, and manipulation, with applications ranging from Implicit Neural Representation editing to weight pruning and function manipulation.

Call for Papers

This workshop is a forum for exchanging ideas and methods for mining and learning with graphs, developing new common understandings of the problems at hand, sharing data sets where applicable, and leveraging existing knowledge from different disciplines. The goal is to bring together researchers from academia and industry to create a forum for discussing recent advances in graph analysis. In doing so, we aim to understand better the overarching principles and the limitations of current methods and to inspire research on new algorithms and techniques for mining and learning with graphs.

To reflect the broad scope of work on mining and learning with graphs, we encourage submissions that span the spectrum from theoretical analysis to algorithms and implementation to applications and empirical studies. We are interested in the full spectrum of graph data, including but not limited to attributed graphs, labeled graphs, knowledge graphs, evolving graphs, transactional graph databases, etc.

We therefore invite submissions on theoretical aspects, algorithms and methods, and applications of the following (non-exhaustive) list of areas:

• Computational or statistical learning theory related to graphs
• Theoretical analysis of graph algorithms or models
• Semi-supervised learning, online learning, active learning, transductive inference, and transfer learning in the context of graphs
• Unsupervised learning and graph clustering
• Interesting pattern mining on graphs and community detection
• Graph kernels and metric learning on graphs
• Graph and vertex embeddings and representation learning on graphs
• Solving combinatorial problems on graphs with ML / data-driven combinatorial optimization
• Explainable, fair, robust, and/or privacy-preserving ML on graphs
• Statistical models of graphs and graph sampling
• Analysis of social media, chemical or biological networks, infrastructure networks, knowledge graphs
• Benchmarking aspects of graph-based learning
• Libraries and tools for all of the above areas

We welcome many kinds of papers, such as, but not limited to:

• Novel research papers
• Demo papers
• Dataset papers
• Work-in-progress papers
• Visionary papers (white papers)
• Appraisal papers of existing methods and tools (e.g., lessons learned)
• Relevant work that has been previously published
• Work that will be presented at the main conference (can be submitted with the regular 16-page limit of ECMLPKDD)

Submission Guidelines Authors should clearly indicate in their abstracts the kinds of submissions that the papers belong to, to help reviewers better understand their contributions. All papers will be peer-reviewed (single-blind). Submissions must be in PDF, long papers no more than 12 pages long, short papers no more than 8 pages long, formatted according to the standard Springer LNCS style required for ECMLPKDD submissions. References and appendix do not count towards the page limit. The accepted papers will be published on the workshop’s website and will not be considered archival for resubmission purposes. Authors whose papers are accepted to the workshop will have the opportunity to participate in a pitch and poster session, and the best four will also be chosen for oral presentation.

Papers should be submitted via CMT: https://cmt3.research.microsoft.com/ECMLPKDDWorkshops2024/
Please select the track MLG: 21st Workshop on Mining and Learning with Graphs

Dual Submission Policy We accept submissions that are currently under review at other venues. However, in this case, our page limits apply. Please also check the dual submission policy of the other venue.

AstraZeneca Healthcare & Bio Track

Schedule

Accepted Papers

1. Alex Romanova (2024):
   Utilizing Pre-Final Vectors from GNN Graph Classification for Enhanced Climate Analysis.
   

   [group A] [pdf] [poster]

2. Andreas Roth (2024):
   A Gentle Introduction to Over-Smoothing.
   

   [group A] [pdf]

3. Andreas Roth, Franka Bause, Nils M Kriege, Thomas Liebig (2024):
   Message-Passing on Directed Acyclic Graphs Prevents Over-Smoothing.
   

   [group B] [pdf]

4. Carlos C. Vonessen Wilson, Florian Grötschla, Roger Wattenhofer (2024):
   Next Level Message-Passing with Hierarchical Support Graphs.
   

   [group B] [pdf]

5. Caterina Graziani, Tamara Drucks, Fabian Jogl, Monica Bianchini, Franco Scarselli, Thomas Gärtner (2024):
   The Expressive Power of Path-Based Graph Neural Networks.
   

   [group B] [pdf]

6. Florian Seiffarth (2024):
   RuleGNNs: A Rule Based Approach for Learning on Graphs.
   

   [group A] [pdf]

7. Golnaz Taheri, Mahnaz Habibi, Tahereh Sedghamiz (2024):
   Machine learning-based Prediction for Drug-Drug Interaction Using a Knowledge Graph.
   

   [group A] [pdf]

8. Leshanshui Yang, Clement Chatelain, Sebastien Adam (2024):
   Inductive Anomaly Detection in Dynamic Graphs with Accumulative Causal Walk Alignment.
   

   [group A] [pdf]

9. Manuel Dileo, Raffaele Olmeda, Margherita Pindaro, Matteo Zignani (2024):
   Graph Machine Learning for fast product development from formulation trials.
   

   [group B] [pdf]

10. Pavel Procházka, Marek Dědič, Lukáš Bajer (2024):
    Convolutional Signal Propagation: A Simple Scalable Algorithm for Hyper-Graphs.
    

    [group B] [pdf]

11. Silvia Beddar-Wiesing, Dominik Köhler (2024):
    Fused Gromov-Wasserstein Distance for Heterogeneous and Temporal Graphs.
    

    [group A] [pdf]

12. Sümeyye Baş, Kiymet Kaya, Resul Tugay, Şule Öğüdücü (2024):
    Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs.
    

    [group B] [pdf] [poster]

13. Thijs Snelleman, Bram M Renting, Holger Hoos, Jan N. Van Rijn (2024):
    Edge-Based Graph Component Pooling.
    

    [group B] [pdf] [poster]

14. Yannis Karmim, Leshanshui Yang, Raphael Fournier-S'niehotta, Nicolas Thome, Clement Chatelain, Sebastien Adam (2024):
    Temporal receptive field in dynamic graph learning: A comprehensive analysis.
    

    [group B] [pdf]

Invited Main Conference Papers

1. Clemens Damke, Eyke Hüllermeier (2024):
   CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks.
   

   [group B]

2. Florian Chen, Felix Q Weitkämper, Sagar Malhotra (2024):
   Understanding Domain-Size Generalization in Markov Logic Networks.
   

   [group A]

3. Franka Bause, Christian Permann, Nils M Kriege (2024):
   Approximating the Graph Edit Distance with Compact Neighborhood Representations.
   

   [group A]

4. Franka Bause, Samir Moustafa, Johannes Langguth, Wilfried Gansterer, Nils M Kriege (2024):
   On the Two Sides of Redundancy in Graph Neural Networks.
   

   [group B]

5. Giuseppe Serra, Mathias Niepert (2024):
   L2XGNN: Learning to Explain Graph Neural Networks.
   

   [group B]

6. Lukas Berner, Henning Meyerhenke (2024):
   Introducing Total Harmonic Resistance for Graph Robustness under Edge Deletions.
   

   [group B]

7. Marco Markwald, Elena Demidova (2024):
   REFUEL: Rule Extraction for Imbalanced Neural Node Classification.
   

   [group A]

8. Matteo Ninniri, Marco Podda, Davide Bacciu (2024):
   Classifier-free graph diffusion for molecular property targeting.
   

   [group A]

9. Richard Serrano, Baptiste Jeudy, Christine Largeron, Charlotte Laclau (2024):
   Reconstructing the Unseen: Attributed Graph Imputation with Optimal Transport.
   

   [group A]

10. Wei Ye, Hao Tian, Shuhao Tang, Xin Sun (2024):
    Enhancing Shortest-Path Graph Kernels via Graph Augmentation.
    

    [group A]

11. Yuhe Bai, Camelia Constantin, Hubert Naacke (2024):
    Leiden-Fusion Partitioning Method for Effective Distributed Training of Graph Embeddings.
    

    [group A]

12. Zeyuan Zhao, Qingqing Ge, Anfeng Cheng, Yiding Liu, Xiang Li, Shuaiqiang Wang (2024):
    HetCAN: A Heterogeneous Graph Cascade Attention Network with Dual-Level Awareness.
    

    [group B]

Awards

During the workshop we held two community votes. One for the best paper award as well as one for the best poster award. Furthermore, we were able to hand out the AstraZeneca Healthcare & Bio Award. We thank Astra Zeneca for the generous sponsorship of our awards!

Best Paper

1. Carlos C. Vonessen Wilson, Florian Grötschla, Roger Wattenhofer (2024):
   Next Level Message-Passing with Hierarchical Support Graphs.
   

   [group B] [pdf]

Best Poster

1. Manuel Dileo, Raffaele Olmeda, Margherita Pindaro, Matteo Zignani (2024):
   Graph Machine Learning for fast product development from formulation trials.
   

   [group B] [pdf]

AstraZeneca Healthcare & Bio Award

1. Thijs Snelleman, Bram M Renting, Holger Hoos, Jan N. Van Rijn (2024):
   Edge-Based Graph Component Pooling.
   

   [group B] [pdf] [poster]

Organizers

• 
  Franka Bause
  University of Vienna
• 
  Thomas Gärtner
  TU Wien
• 
  Nils Kriege
  University of Vienna
• 
  Alice Moallemy-Oureh
  University of Kassel
• 
  Maximilian Thiessen
  TU Wien
• 
  Pascal Welke
  TU Wien

Program Committee

• Andreas Roth (TU Dortmund)
• Antonio Longa (University of Trento)
• Atsushi Miyauchi (CentAI)
• Bo Kang (Ghent University)
• Caterina Graziani (University of Siena)
• Christoph Sandrock (TU Wien)
• Clara Holzhüter (University of Kassel)
• Corinna Coupette (KTH)
• David B. Blumenthal (FAU)
• Fabian Jogl (TU Wien)
• Fabrizio Frasca (Technion)
• Federico Pichi (SISSA)
• Florian Seiffarth (University of Bonn)
• Franco Scarselli (University of Siena)
• Ghaith Mqawass (University of Vienna)
• Giuseppe Alessio D'Inverno (SISSA)
• Ingo Scholtes (University of Würzburg)
• Jan Ramon (INRIA)
• Jefrey Lijffijt (Ghent University)
• Jilles Vreeken (CISPA)
• Josephine Thomas (University of Kassel)
• Lorenz Kummer (University of Vienna)
• Lovro Šubelj (University of Ljubljana)
• Luis Müller (RWTH Aachen)
• Nicolò Navarin (University of Padova)
• Pascal Plettenberg (University of Kassel)
• Patrick Indri (TU Wien)
• Sagar Malhotra (TU Wien)
• Sebastian Dalleiger (KTH)
• Shota Saito (UCL)
• Silvia Beddar-Wiesing (University of Kassel)
• Sohir Maskey (LMU Munich)
• Stefan Neumann (TU Wien)
• Tamara Drucks (TU Wien)
• Till Schulz (Max Planck Institute of Biochemistry)
• Veronica Lachi (University of Siena)
• Ylli Sadikaj (University of Vienna)

Previous Workshops

• 2023, Torino, Italy (co-located with ECMLPKDD)
• 2023, Long Beach, USA (co-located with KDD)
• 2022, Grenoble, France (co-located with ECMLPKDD)
• 2022, Washington, USA (co-located with KDD)
• 2020, virtual (co-located with KDD)
• 2019, Anchorage, USA (co-located with KDD)
• 2018, London, United Kingdom (co-located with KDD)
• 2017, Halifax, Nova Scotia, Canada (co-located with KDD)
• 2016, San Francisco, USA (co-located with KDD)
• 2013, Chicago, USA (co-located with KDD)
• 2012, Edinburgh, Scotland (co-located with ICML)
• 2011, San Diego, USA (co-located with KDD)
• 2010, Washington, USA (co-located with KDD)
• 2009, Leuven, Belgium (co-located with SRL and ILP)
• 2008, Helsinki, Finland (co-located with ICML)
• 2007, Firenze, Italy
• 2006, Berlin, Germany (co-located with ECML and PKDD)
• 2005, Porto, Portugal, October 7, 2005 (co-located with ECML and PKDD)
• 2004, Pisa, Italy, September 24, 2004 (co-located with ECML and PKDD)
• 2003, Cavtat-Dubrovnik, Croatia (co-located with ECML and PKDD)

This page tries to be minimalistic in layout, bandwith, and used tools. It is hosted on github pages, using neat.css stylesheets, and bibtexparser to generate the lists of papers.