User profiles for Kaan Sancak

Kaan Sancak

Georgia Institute of Technology
Verified email at gatech.edu
Cited by 79

Elga: elastic and scalable dynamic graph analysis

K Gabert, K Sancak, MY Özkaya, A Pinar… - Proceedings of the …, 2021 - dl.acm.org
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 …

Vcr-graphormer: A mini-batch graph transformer via virtual connections

…, Z Hua, Y Xie, J Fang, S Zhang, K Sancak… - The Twelfth …, 2024 - openreview.net
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 …

MG-GCN: a scalable multi-gpu GCN training framework

MF Balin, K Sancak, UV Catalyurek - Proceedings of the 51st …, 2022 - dl.acm.org
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 …

A scalable and effective alternative to graph transformers

K Sancak, Z Hua, J Fang, Y Xie, A Malevich… - Proceedings of the …, 2025 - ojs.aaai.org
Graph Neural Networks (GNNs) have shown impressive performance in graph representation
learning, but they face challenges in capturing long-range dependencies due to their …

On symmetric rectilinear partitioning

A Yaşar, MF Balin, X An, K Sancak… - ACM Journal of …, 2022 - dl.acm.org
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 …

On symmetric rectilinear matrix partitioning

A Yaşar, MF Balin, X An, K Sancak… - arXiv preprint arXiv …, 2020 - arxiv.org
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 …

[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

K Sancak, MF Balin, U Catalyurek - The Third Learning on Graphs … - openreview.net
Despite advances in graph learning, increasingly complex models introduce significant
overheads, including prolonged preprocessing and training times, excessive memory …

A Fast and Effective Alternative to Graph Transformers

K Sancak, Z Hua, J Fang, Y Xie, B Long, A Malevich… - openreview.net
Graph Neural Networks (GNNs) have shown impressive performance in graph representation
learning. However, GNNs face challenges in capturing long-range dependencies that limit …

[CITATION][C] Elga v. 1

K Gabert, K Sancak, U Catalyurek, M Ozkaya - 2021 - osti.gov
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 …