Graph Representation Learning (GRL) has gained significant traction within the scientific community, with novel models and techniques developed to understand better and represent the structural complexities of graph-based data. These methods have been applied to various real-world challenges, including social networks, biological systems, recommendation engines, and knowledge graph construction. With recent advancements, the intersection of GRL with algebraic topology in the development of Topological Data Analysis (TDA) has emerged as a promising area, enabling a more profound exploration of data's hidden structures. Furthermore, integrating GRL with fuzzy theory opens new avenues for addressing uncertainty and ambiguity in graph data. The special session on Graph Representation Learning and Applications (GRLA) 2025 at the 17th International Conference on Computational Collective Intelligence (ICCCI 2025) is focused on advanced techniques for graph representation learning, addressing tasks such as classification, clustering, and prediction on graph-structured data, and their applications to both large-scale and small graph datasets. This session aims to provide a platform for researchers and practitioners to explore new research directions and share recent advancements in this rapidly evolving field.
The scope of the session includes, but is not limited to, the following topics:
- Graph neural networks (GNNs), graph convolutional networks (GCNs), and variants
- Integration of algebraic topology with GRL
- Combining GRL with fuzzy theory for handling uncertainty in graph models
- Learning representations for heterogeneous and attributed graphs
- Scalable graph representation learning for large-scale and dynamic graphs
- Temporal graph learning and graph embeddings
- Multi-relational and multi-layer graph learning
- Topological features in graph learning and applications in TDA
- Graph-based transfer learning and domain adaptation
- Applications of GRL in social networks, biology, recommendation systems, etc.
- Interpretability, robustness, and fairness in graph learning models
- Managing noisy, incomplete, and evolving graph data
- Graph learning combined with reinforcement learning and decision-making processes
- Knowledge graph construction and completion using graph-based approaches
- Evaluation and benchmarking of graph learning methods
- Real-world implementations and use cases of GRL techniques
- Applications of ensemble methods in business, engineering, medicine, etc.
