1 code implementation • 19 Oct 2023 • Muhammed Fatih Balin, Dominique LaSalle, Ümit V. Çatalyürek
Significant computational resources are required to train Graph Neural Networks (GNNs) at a large scale, and the process is highly data-intensive.
1 code implementation • 24 Oct 2022 • Muhammed Fatih Balin, Ümit V. Çatalyürek
It is designed to be a direct replacement for Neighbor Sampling (NS) with the same fanout hyperparameter while sampling up to 7 times fewer vertices, without sacrificing quality.
no code implementations • 26 May 2022 • Ümit V. Çatalyürek, Karen D. Devine, Marcelo Fonseca Faraj, Lars Gottesbüren, Tobias Heuer, Henning Meyerhenke, Peter Sanders, Sebastian Schlag, Christian Schulz, Daniel Seemaier, Dorothea Wagner
In recent years, significant advances have been made in the design and evaluation of balanced (hyper)graph partitioning algorithms.
1 code implementation • 17 Oct 2021 • Muhammed Fatih Balin, 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.
1 code implementation • 16 Sep 2020 • Abdurrahman Yaşar, Muhammed Fatih Balin, Xiaojing An, Kaan Sancak, Ümit V. Çatalyürek
More specifically, in this work, we address the problem of symmetric rectilinear partitioning of a square matrix.
Data Structures and Algorithms