Parsa Haddadian

University of Tehran

Tehran, Iran

Parsa (/pārsā/) is a passionate graduate student with a Master’s degree in Algorithms and Computation from the University of Tehran. With a strong foundation in Computer Engineering, earned during his B.Sc. at Razi University, Parsa is now actively exploring new opportunities in higher graduate education.

His primary interests lie in the fields of Machine Learning and Deep Learning, with a particular focus on graph machine learning and the transformative potential of these technologies in healthcare and medicine. Known for his analytical mindset and collaborative spirit, Parsa has worked on various projects that demonstrate his ability to apply theoretical knowledge to real-world challenges.

He is eager to pursue further graduate studies, aiming to contribute to groundbreaking research in the field, and actively participates in machine learning communities to stay at the forefront of innovation.

selected publications

Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective

Parsa Haddadian, Roya Booryaee, Rooholah Abedian, and 1 more author

In 2024 Third International Conference on Distributed Computing and High Performance Computing (DCHPC), Tehran, Iran, 2024

Abs HTML

Over the past ten years, graph representation learning has garnered a lot of attention due to the variety of graph-structured data and its efficiency in both time and space. One essential method for obtaining effective graph representations is graph pooling. Numerous studies on the graph pooling technique have been conducted. Cutting-edge results on a range of graph representation learning tasks were made possible by the combination of graph neural networks and self-attention mechanisms. Nevertheless, the attention mechanism has limitations since it ignores nodes that have no direct connection via an edge but provide valuable network context information. This paper proposes a graph pooling approach based on Personalized PageRank and self-attention, which improves the model to take into account both node properties and graph structure. The experimental findings indicate that, with a suitable number of parameters, the MAGPool approach delivers greater accuracy on the benchmark datasets.