Call for Papers
Special Session — New Frontiers in Graph Neural Networks: Emerging Architectures and Training Paradigms
ESANN 2027 — 35th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Bruges (Belgium) and Online, 21-24 April 2027

Dear colleagues,
We are organizing a special session at the 35th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2027). Please consider submitting your original research findings to our special session: New Frontiers in Graph Neural Networks: Emerging Architectures and Training Paradigms

Important dates:
Paper submission deadline: 18/11/2026 (AoE)
Notification of acceptance: 22/01/2027
Conference: 21/04/2027 - 23/04/2027, Bruges (Belgium)

Submission notes:
Papers submitted to a special session follow exactly the same format, instructions, deadlines and submission procedure as regular submissions, and are reviewed according to the same rules. Please remember to indicate our special session on the paper submission form so that your paper is routed to us. Papers must not exceed 6 pages, including figures and references, and must be prepared with the official ESANN LaTeX or Word template, which you can find here: https://www.esann.org/author_guidelines. The review process is single blind. Please check the author guidelines page and the submissions page for the full and up-to-date instructions (https://www.esann.org/node/6).

Session description:
Graph Neural Networks have become a leading framework for learning from relational and graph-structured data. However, the growing scale and complexity of real-world graphs are exposing the limitations of conventional message-passing architectures and standard training methods. This special session will focus on emerging graph learning models that exploit topological, geometrical, spectral, physical, and dynamical principles. It will also cover novel training paradigms aimed at improving scalability, data efficiency, memory usage, and energy consumption. Topics include but are not limited to:

- Graph representation learning;
- Advanced Graph Neural Architectures;
- Backpropagation-free graph learning;
- Graph structure learning and relational inference;
- Theory of graph neural networks (e.g., expressive power, learnability, negative results);
- Explainability in Graph Learning;
- Learning on complex graphs (e.g., dynamic graphs and heterogeneous graphs);
- Randomized neural networks for graphs (e.g., reservoir computing);
- Recurrent, recursive, and contextual models;
- Scalability, data efficiency, and training techniques of graph neural networks;
- Architectures for foundation models operating on graphs;
- Graph datasets and benchmarks.

The session aims to connect architectural innovation, theoretical understanding, and resource-efficient learning to identify promising directions for the next generation of Graph Neural Networks.

Organizers and contacts:

- Riccardo Cappi (corresponding organizer), University of Padua, Italy - riccardo.cappi@phd.unipd.it

- Caterina Graziani, University of Siena, Italy - caterina.graziani2@unisi.it

- Luca Pasa, University of Padua, Italy - luca.pasa@unipd.it

- Nicolò Navarin, University of Padua, Italy - nicolo.navarin@unipd.it

- Pascal Welke, Lancaster University Leipzig, Germany - p.welke@lancaster.ac.uk

- Franco Scarselli, University of Siena, Italy - franco.scarselli@unisi.it

- Alessandro Sperduti, University of Padua, Italy - alessandro.sperduti@unipd.it

Please don’t hesitate to contact us if you have any questions. We look forward to receiving your submissions.

The organizers