International Conference on Social Network Analysis and Machine Learning (ICSNAML - 26)

This track focuses on the latest developments in graph neural networks and their applications in social network analysis. Researchers are encouraged to present innovative methodologies that enhance the performance of GNNs in various network-related tasks.

This session aims to explore novel algorithms and approaches for community detection within complex networks. Contributions that address scalability, accuracy, and real-world applications of community detection are particularly welcome.

This track invites papers that investigate link prediction methodologies and their implications in social networks. Emphasis will be placed on the integration of machine learning techniques to improve prediction accuracy.

This session will cover innovative techniques for node classification and feature extraction in social networks. Papers that demonstrate the effectiveness of machine learning models in enhancing classification tasks are encouraged.

This track focuses on methodologies for detecting anomalies in network data, with a particular emphasis on machine learning approaches. Contributions that address challenges in real-time detection and scalability are highly sought after.

This session aims to explore the dynamics of network evolution and behavior analysis using machine learning techniques. Papers that provide insights into temporal changes and their implications for network structure are welcome.

This track invites research on predictive modeling techniques applied to social networks, focusing on user behavior and interaction patterns. Contributions that leverage machine learning for enhanced prediction accuracy are encouraged.

This session will explore advanced clustering algorithms tailored for social network data. Papers that propose novel clustering techniques or enhance existing methods through machine learning are particularly welcome.

This track focuses on the analysis of social influence within networks, examining how information spreads and affects user behavior. Contributions that utilize machine learning to model and predict influence dynamics are encouraged.

This session will cover innovative visualization techniques for representing complex network data. Papers that enhance the interpretability of network structures through visual analytics are highly sought after.

This track invites research on both supervised and unsupervised learning methodologies applied to network analysis. Contributions that highlight the strengths and limitations of these approaches in real-world applications are welcome.