Call for Papers

Graph Models for Learning and Recognition (GMLR) Track

The 40th ACM Symposium on Applied Computing (SAC 2025)

March 31 – April 4, 2025 Catania, Italy

https://phuselab.di.unimi.it/GMLR2025/

Important Dates

• Submission of regular papers and SRC abstracts: September 20, 2024
• Notification of papers/SRC acceptance/rejection: October 30, 2024
• Camera-ready copies of accepted papers/SRC: November 29, 2024
• Author registration due date: December 6, 2024

Motivations and topics

The ACM Symposium on Applied Computing (SAC 2025) has been a primary gathering forum for applied computer scientists, computer engineers, software engineers, and application developers from around the world. SAC 2025 is sponsored by the ACM Special Interest Group on Applied Computing (SIGAPP), and will be held in Catania, Italy. The technical track on Graph Models for Learning and Recognition (GMLR) is the fourth edition and is organized within SAC 2025. Graphs have gained a lot of attention in the pattern recognition community thanks to their ability to encode both topological and semantic information. Despite their invaluable descriptive power, their arbitrarily complex structured nature poses serious challenges when they are involved in learning systems. Some (but not all) of challenging concerns are: a non-unique representation of data, heterogeneous attributes (symbolic, numeric, etc.), and so on.

In recent years, due to their widespread applications, graph-based learning algorithms have gained much research interest. Encouraged by the success of CNNs, a wide variety of methods have redefined the notion of convolution and related operations on graphs. These new approaches have in general enabled  effective training and achieved in many cases better performances than competitors, though at the detriment of computational costs. Typical examples of applications dealing  with graph-based representation are: scene graph generation, point clouds classification, and action recognition in computer vision; text classification, inter-relations of documents or words to infer document labels in natural language processing; forecasting traffic speed, volume or the density of roads in traffic networks, whereas in chemistry researchers apply graph-based algorithms to study the graph structure of molecules/compounds.

This track intends to focus on all aspects of graph-based representations and models for learning and recognition tasks. GMLR spans, but is not limited to, the following topics:

• Graph Neural Networks: theory and applications

• Deep learning on graphs

• Graph or knowledge representational learning

• Graphs in pattern recognition

• Graph databases and linked data in AI

• Benchmarks for GNN

• Dynamic, spatial and temporal graphs

• Graph methods in computer vision

• Human behavior and scene understanding

• Social networks analysis

• Data fusion methods in GNN

• Efficient and parallel computation for graph learning algorithms

• Reasoning over knowledge-graphs

• Interactivity, explainability and trust in graph-based learning

• Probabilistic graphical models

• Biomedical data analytics on graphs

Submission Guidelines

Track Chairs

• Vittorio Cuculo (University of Modena e Reggio Emilia)
• Alessandro D'Amelio (University of Milan)
• Giuliano Grossi (University of Milan)
• Raffaella Lanzarotti (University of Milan)
• Jianyi Lin (Università Cattolica del Sacro Cuore)