Graph Theory for Computer Science

15Graph-Based Representation in Artificial Neural Networks

K. Swarupa Rani¹, Boreda Divya², Ravi Uyyala³, Ravindra Changala⁴, G. Ganesh Kumar⁵* and R. Banu Priya⁶

¹Department of IT, PVP Siddhartha Institute of Technology, Kanuru, Vijayawada, India

²Department of CSE (AI & ML), B V RAJU Institute of Technology, Narsapur, Medak, Telangana, India

³Department of Computer Science and Engineering, Chaitanya Bharathi Institute of Technology, Gandipet, Hyderabad, Telangana, India

⁴Department of Computer Science and Engineering, Guru Nanak Institutions Technical Campus, Hyderabad, India

⁵Department of Computer Science and Engineering, Nehru Institute of Technology, Coimbatore, Tamil Nadu, India

⁶Department of Information Technology, Hindusthan Institute of Technology, Coimbatore, Tamil Nadu, India

Abstract

The integration of graph-based representations in artificial neural networks (ANNs) has emerged as a hopeful paradigm for addressing complex learning tasks, particularly in domains characterized by relational data structures. This chapter offers an inclusive overview of the utilization of graph-based representations in ANNs, highlighting their significance, theoretical underpinnings, and practical applications. We begin by elucidating the foundational concepts of graphs and their relevance in modeling interconnected data entities. Subsequently, we delve into the fundamental principles of ANNs and explore various architectures that incorporate graph-based representations, including ...