6 citations · 6 across the 9 of their papers we have counts for
9 papers
Who Should Teach? Confidence-Aware Dual-Teacher Learning for Few-Shot Node Classification on Text-Attributed Graphs
Hojin Kim, Sujin Yoon, Sungsu Lim +2
Text-Attributed Graphs (TAGs) integrate graph structures and node-associated textual attributes, and recent studies have increasingly leveraged Large Language Models (LLMs) to impr…
Multiscale Hypersonic Boundary Layer Reconstruction via Spectral Binning and Subdomain-wise Conditional Diffusion
Hojin Kim, Dibyajyoti Chakraborty, Takahiko Toki +2
We propose a multiscale probabilistic reconstruction framework for hypersonic Couette flow, where near-wall states are inferred from limited top-wall observations using conditional…
Adaptive Diffusion Posterior Sampling for Data and Model Fusion of Complex Nonlinear Dynamical Systems
Dibyajyoti Chakraborty, Hojin Kim, Romit Maulik
High-fidelity numerical simulations of chaotic, high dimensional nonlinear dynamical systems are computationally expensive, necessitating the development of efficient surrogate mod…
Improving the Accuracy of Community Detection on Signed Networks via Community Refinement and Contrastive Learning
Hyunuk Shin, Hojin Kim, Chanyoung Lee +2
Community detection (CD) on signed networks is crucial for understanding how positive and negative relations jointly shape network structure. However, existing CD methods often yie…
Interpretable Diagnostics and Adaptive Data Assimilation for Neural ODEs via Discrete Empirical Interpolation
Hojin Kim, Romit Maulik
We present a framework that leverages the Discrete Empirical Interpolation Method (DEIM) for interpretable deep learning and dynamical system analysis. Although DEIM efficiently ap…
Moment of derivatives of L-functions for two distinct newforms
Seokhyun Choi, Beomho Kim, Hansol Kim +2
We establish an unconditional result concerning the asymptotic formula for the moment of derivatives of -functions over quadratic…
Data-Driven Physics-Informed Neural Networks: A Digital Twin Perspective
Sunwoong Yang, Hojin Kim, Yoonpyo Hong +3
This study explores the potential of physics-informed neural networks (PINNs) for the realization of digital twins (DT) from various perspectives. First, various adaptive sampling…
Interpretable A-posteriori Error Indication for Graph Neural Network Surrogate Models
Shivam Barwey, Hojin Kim, Romit Maulik
Data-driven surrogate modeling has surged in capability in recent years with the emergence of graph neural networks (GNNs), which can operate directly on mesh-based representations…
Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics
Hojin Kim, Varun Shankar, Venkatasubramanian Viswanathan +1
Differentiable physical simulators are proving to be valuable tools for developing data-driven models for computational fluid dynamics (CFD). In particular, these simulators enable…