32 citations · 58 across the 37 of their papers we have counts for
29 papers · 1 filter
How Much Memory Do We Need? Adaptive Memory Gate for Neural Operators
Jihyeon Hur, Yongseok Kwon, Min-Gi Jo +2
Neural operators have emerged as a powerful data-driven approach for solving time-dependent PDEs. Among recent advances, memory-augmented neural operators explicitly incorporate pa…
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
Jeongwhan Choi, Jongwoo Kim, Woosung Kang +1
One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face a fundamental limitation: th…
Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
Yehjin Shin, Seojin Kim, Noseong Park
State-space models (SSMs) offer efficient alternatives to attention with linear-time recurrence. Mamba2, a recent SSM-based language model, uses selective input gating and a multi-…
HINTS: Extraction of Human Insights from Time-Series Without External Sources
Sheo Yon Jhin, Noseong Park
Human decision-making, emotions, and collective psychology are complex factors that shape the temporal dynamics observed in financial and economic systems. Many recent time series…
How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts
Sumin Park, Noseong Park
Finding the optimal configuration of Sparse Mixture-ofExperts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE arc…
Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?
Jeongwhan Choi, Woosung Kang, Minseo Kim +2
Foundation models pretrained on large data have demonstrated remarkable zero-shot generalization capabilities across domains. Building on the success of TabPFN for tabular data and…
TSGM: Regular and Irregular Time-series Generation using Score-based Generative Models
Haksoo Lim, Jaehoon Lee, Sewon Park +2
Score-based generative models (SGMs) have demonstrated unparalleled sampling quality and diversity in numerous fields, such as image generation, voice synthesis, and tabular data s…
Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs
Jeongwhan Choi, Seungjun Park, Sumin Park +2
Graph Neural Networks (GNNs) have emerged as powerful tools for learning on graph-structured data, but often struggle to balance local and global information. While graph Transform…
Learning Low Rank Neural Representations of Hyperbolic Wave Dynamics from Data
Woojin Cho, Kookjin Lee, Noseong Park +2
We present a data-driven dimensionality reduction method that is well-suited for physics-based data representing hyperbolic wave propagation. The method utilizes a specialized neur…
PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling
Minju Jo, Woojin Cho, Uvini Balasuriya Mudiyanselage +3
Scientific machine learning often involves representing complex solution fields that exhibit high-frequency features such as sharp transitions, fine-scale oscillations, and localiz…
Neural Functions for Learning Periodic Signal
Woojin Cho, Minju Jo, Kookjin Lee +1
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 lear…
Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain
Hyowon Wi, Jeongwhan Choi, Noseong Park
Transformers have demonstrated remarkable performance across diverse domains. The key component of Transformers is self-attention, which learns the relationship between any two tok…
Possibility for Proactive Anomaly Detection
Jinsung Jeon, Jaehyeon Park, Sewon Park +3
Time-series anomaly detection, which detects errors and failures in a workflow, is one of the most important topics in real-world applications. The purpose of time-series anomaly d…
PIORF: Physics-Informed Ollivier-Ricci Flow for Long-Range Interactions in Mesh Graph Neural Networks
Youn-Yeol Yu, Jeongwhan Choi, Jaehyeon Park +2
Recently, data-driven simulators based on graph neural networks have gained attention in modeling physical systems on unstructured meshes. However, they struggle with long-range de…
Unveiling the Potential of Superexpressive Networks in Implicit Neural Representations
Uvini Balasuriya Mudiyanselage, Woojin Cho, Minju Jo +2
In this study, we examine the potential of one of the ``superexpressive'' networks in the context of learning neural functions for representing complex signals and performing machi…
MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data
Mingu Kang, Dongseok Lee, Woojin Cho +5
Large language models (LLMs), like ChatGPT, have shown that even trained with noisy prior data, they can generalize effectively to new tasks through in-context learning (ICL) and p…
FastLRNR and Sparse Physics Informed Backpropagation
Woojin Cho, Kookjin Lee, Noseong Park +2
We introduce Sparse Physics Informed Backpropagation (SPInProp), a new class of methods for accelerating backpropagation for a specialized neural network architecture called Low Ra…
Bridging Dynamic Factor Models and Neural Controlled Differential Equations for Nowcasting GDP
Seonkyu Lim, Jeongwhan Choi, Noseong Park +4
Gross domestic product (GDP) nowcasting is crucial for policy-making as GDP growth is a key indicator of economic conditions. Dynamic factor models (DFMs) have been widely adopted…
Parameterized Physics-informed Neural Networks for Parameterized PDEs
Woojin Cho, Minju Jo, Haksoo Lim +4
Complex physical systems are often described by partial differential equations (PDEs) that depend on parameters such as the Reynolds number in fluid mechanics. In applications such…
PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
Jeongwhan Choi, Sumin Park, Hyowon Wi +2
Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures,…
Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization
Sheo Yon Jhin, Seojin Kim, Noseong Park
Time series forecasting has been an essential field in many different application areas, including economic analysis, meteorology, and so forth. The majority of time series forecas…
Efficiently Parameterized Neural Metriplectic Systems
Anthony Gruber, Kookjin Lee, Haksoo Lim +2
Metriplectic systems are learned from data in a way that scales quadratically in both the size of the state and the rank of the metriplectic data. Besides being provably energy con…
Operator-learning-inspired Modeling of Neural Ordinary Differential Equations
Woojin Cho, Seunghyeon Cho, Hyundong Jin +6
Neural ordinary differential equations (NODEs), one of the most influential works of the differential equation-based deep learning, are to continuously generalize residual networks…
Continuous-time Autoencoders for Regular and Irregular Time Series Imputation
Hyowon Wi, Yehjin Shin, Noseong Park
Time series imputation is one of the most fundamental tasks for time series. Real-world time series datasets are frequently incomplete (or irregular with missing observations), in…