Author name cluster

Minju Jo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

ICLR Conference 2025 Conference Paper

Neural Functions for Learning Periodic Signal

Woojin Cho
Minju Jo
Kookjin Lee
Noseong Park

As function approximators, deep neural networks have served as an effective tool to represent various signal types. Recent approaches utilize multi-layer perceptrons (MLPs) to learn a nonlinear mapping from a coordinate to its corresponding signal, facilitating the learning of continuous neural representations from discrete data points. Despite notable successes in learning diverse signal types, coordinate-based MLPs often face issues of overfitting and limited generalizability beyond the training region, resulting in subpar extrapolation performance. This study addresses scenarios where the underlying true signals exhibit periodic properties, either spatially or temporally. We propose a novel network architecture, which extracts periodic patterns from measurements and leverages this information to represent the signal, thereby enhancing generalization and improving extrapolation performance. We demonstrate the efficacy of the proposed method through comprehensive experiments, including the learning of the periodic solutions for differential equations, and time series imputation (interpolation) and forecasting (extrapolation) on real-world datasets.

Details

NeurIPS Conference 2025 Conference Paper

PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling

Minju Jo
Woojin Cho
Uvini Balasuriya Mudiyanselage
Seungjun Lee
Noseong Park
Kookjin Lee

Scientific machine learning often involves representing complex solution fields that exhibit high-frequency features such as sharp transitions, fine-scale oscillations, and localized structures. While implicit neural representations (INRs) have shown promise for continuous function modeling, capturing such high-frequency behavior remains a challenge—especially when modeling multiple solution fields with a shared network. Prior work addressing spectral bias in INRs has primarily focused on single-instance settings, limiting scalability and generalization. In this work, we propose Global Fourier Modulation (GFM), a novel modulation technique that injects high-frequency information at each layer of the INR through Fourier-based reparameterization. This enables compact and accurate representation of multiple solution fields using low-dimensional latent vectors. Building upon GFM, we introduce PDEfuncta, a meta-learning framework designed to learn multi-modal solution fields and support generalization to new tasks. Through empirical studies on diverse scientific problems, we demonstrate that our method not only improves representational quality but also shows potential for forward and inverse inference tasks without the need for retraining.

PDF Details

ICML Conference 2024 Conference Paper

Parameterized Physics-informed Neural Networks for Parameterized PDEs

Woojin Cho
Minju Jo
Haksoo Lim
Kookjin Lee
Dongeun Lee 0001
Sanghyun Hong 0001
Noseong Park

Complex physical systems are often described by partial differential equations (PDEs) that depend on parameters such as the Raynolds number in fluid mechanics. In applications such as design optimization or uncertainty quantification, solutions of those PDEs need to be evaluated at numerous points in the parameter space. While physics-informed neural networks (PINNs) have emerged as a new strong competitor as a surrogate, their usage in this scenario remains underexplored due to the inherent need for repetitive and time-consuming training. In this paper, we address this problem by proposing a novel extension, parameterized physics-informed neural networks (P$^2$INNs). P$^2$INNs enable modeling the solutions of parameterized PDEs via explicitly encoding a latent representation of PDE parameters. With the extensive empirical evaluation, we demonstrate that P$^2$INNs outperform the baselines both in accuracy and parameter efficiency on benchmark 1D and 2D parameterized PDEs and are also effective in overcoming the known “failure modes”.

Details

IJCAI Conference 2023 Conference Paper

Hawkes Process Based on Controlled Differential Equations

Minju Jo
Seungji Kook
Noseong Park

Hawkes processes are a popular framework to model the occurrence of sequential events, i. e. , occurrence dynamics, in several fields such as social diffusion. In real-world scenarios, the inter-arrival time among events is irregular. However, existing neural network-based Hawkes process models not only i) fail to capture such complicated irregular dynamics, but also ii) resort to heuristics to calculate the log-likelihood of events since they are mostly based on neural networks designed for regular discrete inputs. To this end, we present the concept of Hawkes process based on controlled differential equations (HP-CDE), by adopting the neural controlled differential equation (neural CDE) technology which is an analogue to continuous RNNs. Since HP-CDE continuously reads data, i) irregular time-series datasets can be properly treated preserving their uneven temporal spaces, and ii) the log-likelihood can be exactly computed. Moreover, as both Hawkes processes and neural CDEs are first developed to model complicated human behavioral dynamics, neural CDE-based Hawkes processes are successful in modeling such occurrence dynamics. In our experiments with 4 real-world datasets, our method outperforms existing methods by non-trivial margins.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Learnable Path in Neural Controlled Differential Equations

Sheo Yon Jhin
Minju Jo
Seungji Kook
Noseong Park

Neural controlled differential equations (NCDEs), which are continuous analogues to recurrent neural networks (RNNs), are a specialized model in (irregular) time-series processing. In comparison with similar models, e.g., neural ordinary differential equations (NODEs), the key distinctive characteristics of NCDEs are i) the adoption of the continuous path created by an interpolation algorithm from each raw discrete time-series sample and ii) the adoption of the Riemann--Stieltjes integral. It is the continuous path which makes NCDEs be analogues to continuous RNNs. However, NCDEs use existing interpolation algorithms to create the path, which is unclear whether they can create an optimal path. To this end, we present a method to generate another latent path (rather than relying on existing interpolation algorithms), which is identical to learning an appropriate interpolation method. We design an encoder-decoder module based on NCDEs and NODEs, and a special training method for it. Our method shows the best performance in both time-series classification and forecasting.

PDF Details DOI

ICLR Conference 2022 Conference Paper

LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations

Jaehoon Lee 0002
Jinsung Jeon
Sheo Yon Jhin
Jihyeon Hyeong
Jayoung Kim 0002
Minju Jo
Seungji Kook
Noseong Park

The problem of processing very long time-series data (e.g., a length of more than 10,000) is a long-standing research problem in machine learning. Recently, one breakthrough, called neural rough differential equations (NRDEs), has been proposed and has shown that it is able to process such data. Their main concept is to use the log-signature transform, which is known to be more efficient than the Fourier transform for irregular long time-series, to convert a very long time-series sample into a relatively shorter series of feature vectors. However, the log-signature transform causes non-trivial spatial overheads. To this end, we present the method of LOweR-Dimensional embedding of log-signature (LORD), where we define an NRDE-based autoencoder to implant the higher-depth log-signature knowledge into the lower-depth log-signature. We show that the encoder successfully combines the higher-depth and the lower-depth log-signature knowledge, which greatly stabilizes the training process and increases the model accuracy. In our experiments with benchmark datasets, the improvement ratio by our method is up to 75\% in terms of various classification and forecasting evaluation metrics.

Details

YNIMG Journal 2019 Journal Article

Advances in gradient echo myelin water imaging at 3T and 7T

Hyeong-Geol Shin
Se-Hong Oh
Masaki Fukunaga
Yoonho Nam
Doohee Lee
Woojin Jung
Minju Jo
Sooyeon Ji

Gradient echo myelin water imaging (GRE-MWI) is an MRI technique to measure myelin concentration and involves the analysis of signal decay characteristics of the multi-echo gradient echo data. The method provides a myelin water fraction as a quantitative biomarker for myelin. In this work, a new sequence and post-processing methods were proposed to generate high quality GRE-MWI images at 3T and 7T. In order to capture the rapidly decaying myelin water signals, a bipolar readout GRE sequence was designed with "gradient pairing, " compensating for the eddy current effects. The flip angle dependency from the multi-compartmental T1 effects was explored and avoided using a 2D multi-slice acquisition with a long TR. Additionally, the sequence was tested for the effects of inflow and magnetization transfer and demonstrated robustness to these error sources. Lastly, the temporal and spatial B0 inhomogeneity effects were mitigated by using the B0 navigator and field inhomogeneity corrections. Using the method, high-quality myelin water images were successfully generated for the in-vivo human brain at both field strengths. When the myelin water fraction at 3T and 7T were compared, they showed a good correlation (R2 ≥ 0. 88; p < 0. 001) with a larger myelin water fraction at 7T. The proposed method also opens the possibility of high resolution (isotropic 1. 5 mm resolution) myelin water mapping at 7T.

Details DOI