Kamal Berahmand
Details
-
College: School of Engineering
-
Department: School of Engineering
-
Campus: City Campus Australia
-
kamal.berahmand@rmit.edu.au
About
Dr. Kamal Berahmand is a Postdoctoral Research Fellow in the School of Computing Technologies at RMIT University, Melbourne. His research spans machine learning, graph representation learning, and network science, with a strong emphasis on both theoretical innovation and real-world applications. With a solid track record of impactful publications and cross-disciplinary collaborations, he is dedicated to advancing scalable and interpretable graph-based methods that can support complex systems such as transportation networks, social platforms, and biological systems.
Teaching interests
-
Graph Neural Networks (GNNs)
-
Scalable and Efficient Graph Representation Learning
-
Higher-Order Network Structures
-
Graph Structure Learning and Topology Optimization
-
Graph Anomaly Detection
-
Network Science and Complex Systems
-
Semi-supervised and Self-supervised Learning on Graphs
-
Knowledge Graph Embedding and Reasoning
-
Spatiotemporal Graph Modeling (e.g., Traffic Networks)
Research interests
Dr. Berahmand’s work focuses on designing efficient and robust algorithms for mining and modeling graph-structured data. He is particularly interested in how graph-based methods can be tailored to solve fundamental problems like node classification, link prediction, graph clustering, and anomaly detection. His current research explores the role of higher-order dependencies in real-world networks, such as traffic and infrastructure systems, as well as methods to enhance the scalability and explainability of graph neural networks (GNNs).
He actively contributes to both academic and applied projects, and his research outputs have been adopted in interdisciplinary contexts, reinforcing the versatility of graph learning frameworks across domains.
