34 citations
- National Centre for Nuclear ResearchPL68 papers
- Sungkyunkwan UniversityKR68 papers
- Université Libre de BruxellesBE68 papers
- Yonsei UniversityKR68 papers
- Peking UniversityCN66 papers
- Seoul National UniversityKR66 papers
- University of Wisconsin–MadisonUS66 papers
- California Institute of TechnologyUS65 papers
- Cornell UniversityUS65 papers
- Eötvös Loránd UniversityHU65 papers
- HUN-REN Wigner Research Centre for PhysicsHU65 papers
- Massachusetts Institute of TechnologyUS65 papers
6 papers · 1 filter
CADGL: Context-Aware Deep Graph Learning for Predicting Drug-Drug Interactions
Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam +2
Examining Drug-Drug Interactions (DDIs) is a pivotal element in the process of drug development. DDIs occur when one drug's properties are affected by the inclusion of other drugs.…
Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study
Xian-Rong Zhang, Yue-Jiao Gong, Yuan-Ting Zhong +2
In many-task optimization scenarios, surrogate models are valuable for mitigating the computational burden of repeated fitness evaluations across tasks. This study proposes a novel…
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…
Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
Hyeong-Gun Joo, Songnam Hong, Seunghwan Lee +1
Federated learning (FL) faces challenges in ensuring both privacy and communication efficiency, particularly in resource-constrained environments such as Internet of Things (IoT) a…
Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning
Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko
We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite d…
MAC: An Efficient Gradient Preconditioning using Mean Activation Approximated Curvature
Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko
Second-order optimization methods for training neural networks, such as KFAC, exhibit superior convergence by utilizing curvature information of loss landscape. However, it comes a…