Muhammed Fatih Balin — accepted AI-conference papers

2025

A Scalable and Effective Alternative to Graph Transformers

Kaan Sancak, Zhigang Hua, Jin Fang, Yan Xie, Andrey Malevich, Bo Long +2

AAAI 2025technical

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 expressive power. To address this, Graph Transformers (GTs) were introduced, utilizing self-attention mechanism to effec…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs

Muhammed Fatih Balin, Umit Catalyurek

NeurIPS 2023poster

Graph Neural Networks (GNNs) have received significant attention recently, but training them at a large scale remains a challenge. Mini-batch training coupled with sampling is used to alleviate this challenge. However, existing approaches either suffer from the neighborhood explosion phenomenon or h…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗