5 citations · 5 across the 5 of their papers we have counts for
6 papers
BLISS: Bandit Layer Importance Sampling Strategy for Efficient Training of Graph Neural Networks
Omar Alsaqa, Linh Thi Hoang, Muhammed Fatih Balin
Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their application to large graphs is hindered by computational costs. The need to proce…
A Scalable and Effective Alternative to Graph Transformers
Kaan Sancak, Zhigang Hua, Jin Fang +5
Graph Neural Networks (GNNs) have shown impressive performance in graph representation learning, but they face challenges in capturing long-range dependencies due to their limited…
SGORP: A Subgradient-based Method for d-Dimensional Rectilinear Partitioning
Muhammed Fatih Balin, Xiaojing An, Abdurrahman Yaşar +1
Partitioning for load balancing is a crucial first step to parallelize any type of computation. In this work, we propose SGORP, a new spatial partitioning method based on Subgradie…
Cooperative Minibatching in Graph Neural Networks
Muhammed Fatih Balin, Dominique LaSalle, Ümit V. Çatalyürek
Training large scale Graph Neural Networks (GNNs) requires significant computational resources, and the process is highly data-intensive. One of the most effective ways to reduce r…
MG-GCN: Scalable Multi-GPU GCN Training Framework
Muhammed Fatih Balın, Kaan Sancak, Ümit V. Çatalyürek
Full batch training of Graph Convolutional Network (GCN) models is not feasible on a single GPU for large graphs containing tens of millions of vertices or more. Recent work has sh…
On Symmetric Rectilinear Matrix Partitioning
Abdurrahman Yaşar, Muhammed Fatih Balin, Xiaojing An +2
Even distribution of irregular workload to processing units is crucial for efficient parallelization in many applications. In this work, we are concerned with a spatial partitionin…