From the 1 of 803 papers with an AI index.
9.8k citations
- Seoul National UniversityKR390 papers
- Sungkyunkwan UniversityKR389 papers
- Tata Institute of Fundamental ResearchIN374 papers
- National Taiwan UniversityTW367 papers
- National Central UniversityTW364 papers
- Kyungpook National UniversityKR355 papers
- Panjab UniversityIN339 papers
- Charles UniversityCZ331 papers
- Yonsei UniversityKR329 papers
- Institute of High Energy PhysicsCN310 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di TorinoIT308 papers
- University of FloridaUS308 papers
16 papers · 1 filter
Accelerating Storage-Based Training for Graph Neural Networks
Myung-Hwan Jang, Jeong-Min Park, Yunyong Ko +1
Graph neural networks (GNNs) have achieved breakthroughs in various real-world downstream tasks due to their powerful expressiveness. As the scale of real-world graphs has been con…
NysAct: A Scalable Preconditioned Gradient Descent using Nystrom Approximation
Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko
Adaptive gradient methods are computationally efficient and converge quickly, but they often suffer from poor generalization. In contrast, second-order methods enhance convergence…
An Adaptive Method Stabilizing Activations for Enhanced Generalization
Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko
We introduce AdaAct, a novel optimization algorithm that adjusts learning rates according to activation variance. Our method enhances the stability of neuron outputs by incorporati…
Transfer-Learning-Based Autotuning Using Gaussian Copula
Thomas Randall, Jaehoon Koo, Brice Videau +6
As diverse high-performance computing (HPC) systems are built, many opportunities arise for applications to solve larger problems than ever before. Given the significantly increase…
CBP: Backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method
Guhyun Kim, Doo Seok Jeong
Backward propagation of errors (backpropagation) is a method to minimize objective functions (e.g., loss functions) of deep neural networks by identifying optimal sets of weights a…
Scheduling Optimization Techniques for Neural Network Training
Hyungjun Oh, HyeongJu Kim, Jiwon Seo
Neural network training requires a large amount of computation and thus GPUs are often used for the acceleration. While they improve the performance, GPUs are underutilized during…