Workshop 

1st Workshop Graph-based knowledge extraction from real-world data

within

2024 IEEE Int Conf on Artificial Intelligence for Data & Knowledge Engineering

11 - 13 December 2024

Submission deadline: 23 October  28 October 2024

Recently, graphs have become a useful tool for extracting knowledge from complex, structured, real-world data. By representing entities as nodes and their relationships as edges, they offer a flexible framework for modelling diverse domains such as social networks, bioinformatics, financial systems, cybersecurity, and biomedical data analysis. Unlike traditional data structures, such as grids or sequences, graphs capture non-Euclidean structures often present in real-world scenarios, offering a more intuitive and accurate representation of complex relationships and allowing knowledge extraction and pattern discovery.

The primary goal of this workshop is to provide a comprehensive exploration of graph-based knowledge extraction techniques, including, but not limited to, theoretical foundations and practical applications.

Motivation

The increasing complexity of real-world data demands advanced tools capable of capturing non-Euclidean structures. Graphs provide a robust framework for analyzing complex data, offering significant advantages in bioinformatics, social networks, finance, etc.  This workshop is a valuable platform for researchers and practitioners to explore the latest advancements, exchange insights, and foster collaboration, driving innovation in graph-based data analysis and accelerating knowledge discovery.

Topics

• Modeling complex systems with graphs

• Role of graphs in biology, finance, and communication networks

• Techniques for graph construction from raw data

• Large-scale graph processing and distributed algorithms

• Foundations of graph theory and its application to Graph Neural Networks

• Theoretical underpinnings of Graph Neural Networks

• Application of Graph Neural Networks  for real-world data analysis

• Representation of real-world data through graphs 

• Advances in Graph Neural Networks  architectures and training techniques

• Knowledge extraction in bioinformatics, financial systems, social networks, ecological informatics, biomedical engineering and cybersecurity

• Integration of Graph Neural Networks  with other machine learning models

• Graph Neural Network Explainability

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference. Papers must be written in English be prepared using IEEE templates

https://www.ieee.org/conferences/publishing/templates.html

• Latex 

• Doc

• Overleaf

The following paper categories are welcome:

• Short Papers describing a small focused contributions, late-breaking developments, or in-progress work and must not exceed 4 pages.

• Long Papers describing full contribution with well supported methods and adequate related works, page limit is 8 pages.

The submission page is at: https://easychair.org/my/conference?conf=gkerd2024

Program Committee 

• Gabriella Casalino, University of Bari, Italy

• Antonino Fiannaca, Institute for High-Performance Computing and Networking - National Research Council of Italy 

• Massimo La Rosa, Institute for High-Performance Computing and Networking - National Research Council of Italy 

• Raffaella Lanzarotti, University of Milan, Italy

• Carmelo Militello, Institute for High-Performance Computing and Networking - National Research Council of Italy 

• Francesco Prinzi, University of Palermo, Italy

• Vincenzo Mariano Scarrica, Università degli Studi di Napoli "Parthenope", Italy

• Gennario Vessio, University di Bari, Italy