User profiles for Kaan Sancak
Kaan SancakGeorgia Institute of Technology Verified email at gatech.edu Cited by 79 |
Elga: elastic and scalable dynamic graph analysis
Modern graphs are not only large, but rapidly changing. The rate of change can vary
significantly along with the computational cost. Existing distributed graph analysis systems have …
significantly along with the computational cost. Existing distributed graph analysis systems have …
Vcr-graphormer: A mini-batch graph transformer via virtual connections
Graph transformer has been proven as an effective graph learning method for its adoption of
attention mechanism that is capable of capturing expressive representations from complex …
attention mechanism that is capable of capturing expressive representations from complex …
MG-GCN: a scalable multi-gpu GCN training framework
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 shown …
GPU for large graphs containing tens of millions of vertices or more. Recent work has shown …
A scalable and effective alternative to graph transformers
Graph Neural Networks (GNNs) have shown impressive performance in graph representation
learning, but they face challenges in capturing long-range dependencies due to their …
learning, but they face challenges in capturing long-range dependencies due to their …
On symmetric rectilinear partitioning
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 partitioning called …
in many applications. In this work, we are concerned with a spatial partitioning called …
On symmetric rectilinear matrix partitioning
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 partitioning called …
in many applications. In this work, we are concerned with a spatial partitioning called …
[CITATION][C] Galatasaray'a adanmış bir ömür: Erden Kuntalp
Ö Dülger, D Kantaş, FB Özbek, AK Kayalı, K Sancak - repository.bilkent.edu.tr
Do We Really Need Complicated Graph Learning Models?--A Simple but Effective Baseline
Despite advances in graph learning, increasingly complex models introduce significant
overheads, including prolonged preprocessing and training times, excessive memory …
overheads, including prolonged preprocessing and training times, excessive memory …
A Fast and Effective Alternative to Graph Transformers
Graph Neural Networks (GNNs) have shown impressive performance in graph representation
learning. However, GNNs face challenges in capturing long-range dependencies that limit …
learning. However, GNNs face challenges in capturing long-range dependencies that limit …
[CITATION][C] Elga v. 1
SAND2021-4635 O Elga is a software system that provides distributed and elastic computation
for temporal graph algorithms. Sandia National Laboratories is a multimission laboratory …
for temporal graph algorithms. Sandia National Laboratories is a multimission laboratory …