Search Results for author:
Found 60 papers, 31 papers with code
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
Extensively evaluating methods with seven image recognition benchmarks, we show that the proposed PAC-FNO improves the performance of existing baseline models on images with various resolutions by up to 77. 1% and various types of natural variations in the images at inference.
Continuous-time Autoencoders for Regular and Irregular Time Series Imputation
However, it has been overlooked for a long time to design an imputation method based on continuous-time recurrent neural networks (RNNs), i. e., neural controlled differential equations (NCDEs).
RDGCL: Reaction-Diffusion Graph Contrastive Learning for Recommendation
Contrastive learning (CL) has emerged as a promising technique for improving recommender systems, addressing the challenge of data sparsity by leveraging self-supervised signals from raw data.
Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer
These methods are typically designed to i) reduce the computational cost in solving physical dynamics and/or ii) propose techniques to enhance the solution accuracy in fluid and rigid body dynamics.
An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention
In the SR domain, we, for the first time, show that the same problem occurs.
Ranked #1 on
Sequential Recommendation
on MovieLens 1M
Operator-learning-inspired Modeling of Neural Ordinary Differential Equations
Neural ordinary differential equations (NODEs), one of the most influential works of the differential equation-based deep learning, are to continuously generalize residual networks and opened a new field.
Polynomial-based Self-Attention for Table Representation learning
Structured data, which constitutes a significant portion of existing data types, has been a long-standing research topic in the field of machine learning.
Graph Convolutions Enrich the Self-Attention in Transformers!
Transformers, renowned for their self-attention mechanism, have achieved state-of-the-art performance across various tasks in natural language processing, computer vision, time-series modeling, etc.
Long-term Time Series Forecasting based on Decomposition and Neural Ordinary Differential Equations
Long-term time series forecasting (LTSF) is a challenging task that has been investigated in various domains such as finance investment, health care, traffic, and weather forecasting.
MadSGM: Multivariate Anomaly Detection with Score-based Generative Models
The time-series anomaly detection is one of the most fundamental tasks for time-series.
Precursor-of-Anomaly Detection for Irregular Time Series
Unlike conventional anomaly detection, which focuses on determining whether a given time series observation is an anomaly or not, PoA detection aims to detect future anomalies before they happen.
Hawkes Process Based on Controlled Differential Equations
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.
CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis
With growing attention to tabular data these days, the attempt to apply a synthetic table to various tasks has been expanded toward various scenarios.
Graph Neural Rough Differential Equations for Traffic Forecasting
A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing.
Ranked #2 on
Traffic Prediction
on PeMSD7(L)
Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration
Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-profile systems.
Regular Time-series Generation using SGM
We propose a conditional score network for the time-series generation domain.
Learnable Path in Neural Controlled Differential Equations
Neural controlled differential equations (NCDEs), which are continuous analogues to recurrent neural networks (RNNs), are a specialized model in (irregular) time-series processing.
GREAD: Graph Neural Reaction-Diffusion Networks
In particular, diffusion equations have been widely used for designing the core processing layer of GNNs, and therefore they are inevitably vulnerable to the notorious oversmoothing problem.
Time Series Forecasting with Hypernetworks Generating Parameters in Advance
Forecasting future outcomes from recent time series data is not easy, especially when the future data are different from the past (i. e. time series are under temporal drifts).
Blurring-Sharpening Process Models for Collaborative Filtering
Various methods have been proposed for collaborative filtering, ranging from matrix factorization to graph convolutional methods.
Ranked #1 on
Collaborative Filtering
on Gowalla
TimeKit: A Time-series Forecasting-based Upgrade Kit for Collaborative Filtering
We present a time-series forecasting-based upgrade kit (TimeKit), which works in the following way: it i) first decides a base collaborative filtering algorithm, ii) extracts user/item embedding vectors with the base algorithm from user-item interaction logs incrementally, e. g., every month, iii) trains our time-series forecasting model with the extracted time- series of embedding vectors, and then iv) forecasts the future embedding vectors and recommend with their dot-product scores owing to a recent breakthrough in processing complicated time- series data, i. e., neural controlled differential equations (NCDEs).
Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting
However, parameterization of dynamics using a neural network makes it difficult for humans to identify causal structures in the data.
STaSy: Score-based Tabular data Synthesis
Our proposed training strategy includes a self-paced learning technique and a fine-tuning strategy, which further increases the sampling quality and diversity by stabilizing the denoising score matching training.
GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
Time series synthesis is an important research topic in the field of deep learning, which can be used for data augmentation.
Phishing URL Detection: A Network-based Approach Robust to Evasion
Many cyberattacks start with disseminating phishing URLs.
Prediction-based One-shot Dynamic Parking Pricing
Owing to the continuous and bijective characteristics of NODEs, in addition, we design a one-shot price optimization method given a pre-trained prediction model, which requires only one iteration to find the optimal solution.
An Empirical Study on the Membership Inference Attack against Tabular Data Synthesis Models
Tabular data typically contains private and important information; thus, precautions must be taken before they are shared with others.
AdamNODEs: When Neural ODE Meets Adaptive Moment Estimation
In this work, we propose adaptive momentum estimation neural ODEs (AdamNODEs) that adaptively control the acceleration of the classical momentum-based approach.
SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations
Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity.
SOS: Score-based Oversampling for Tabular Data
To our knowledge, we are the first presenting a score-based tabular data oversampling method.
EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting
Deep learning inspired by differential equations is a recent research trend and has marked the state of the art performance for many machine learning tasks.
LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations
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.
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
To deal with the performance drop induced by quantization errors, a popular method is to use training data to fine-tune quantized networks.
Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis
First, we can further improve the synthesis quality, by decreasing the negative log-density of real records in the process of adversarial training.
Graph Neural Controlled Differential Equations for Traffic Forecasting
A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing.
Ranked #3 on
Traffic Prediction
on PeMSD7(L)
Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis
First, we can further improve the synthesis quality, by decreasing the negative log-density of real records in the process of adversarial training.
Linear, or Non-Linear, That is the Question!
To our knowledge, we are the first who design a hybrid method and report the correlation between the graph centrality and the linearity/non-linearity of nodes.
Climate Modeling with Neural Diffusion Equations
On the other hand, neural ordinary differential equations (NODEs) are to learn a latent governing equation of ODE from data.
Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries.
Ranked #1 on
Data Free Quantization
on CIFAR-100
IIT-GAN: Irregular and Intermittent Time-series Synthesis with Generative Adversarial Networks
In this paper, we solve the problem of synthesizing irregular and intermittent time-series where values can be missing and may not have specific frequencies, which is far more challenging than existing settings.
ConCoDE: Hard-constrained Differentiable Co-Exploration Method for Neural Architectures and Hardware Accelerators
To handle the hard constraint problem of differentiable co-exploration, we propose ConCoDE, which searches for hard-constrained solutions without compromising the global design objectives.
Regularizing Image Classification Neural Networks with Partial Differential Equations
In other words, the knowledge contained by the learned governing equation can be injected into the neural network which approximates the PDE solution function.
Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting
Neural networks inspired by differential equations have proliferated for the past several years.
LightMove: A Lightweight Next-POI Recommendation for Taxicab Rooftop Advertising
Among various such mobile billboards, taxicab rooftop devices are emerging in the market as a brand new media.
LT-OCF: Learnable-Time ODE-based Collaborative Filtering
In this work, we extend them based on neural ordinary differential equations (NODEs), because the linear GCN concept can be interpreted as a differential equation, and present the method of Learnable-Time ODE-based Collaborative Filtering (LT-OCF).
Ranked #1 on
Recommendation Systems
on Amazon-book
OCT-GAN: Neural ODE-based Conditional Tabular GANs
Synthesizing tabular data is attracting much attention these days for various purposes.
ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equations
Neural ordinary differential equations (NODEs) presented a new paradigm to construct (continuous-time) neural networks.
Large-Scale Data-Driven Airline Market Influence Maximization
On top of the prediction models, we define a budget-constrained flight frequency optimization problem to maximize the market influence over 2, 262 routes.
Neural Partial Differential Equations
Neural ordinary differential equations (neural ODEs) introduced an approach to approximate a neural network as a system of ODEs after considering its layer as a continuous variable and discretizing its hidden dimension.
DISE: Dynamic Integrator Selection to Minimize Forward Pass Time in Neural ODEs
Because it is not the case that every input requires the advanced integrator, we design an auxiliary neural network to choose an appropriate integrator given input to decrease the overall inference time without significantly sacrificing accuracy.
DPM: A Novel Training Method for Physics-Informed Neural Networks in Extrapolation
We present a method for learning dynamics of complex physical processes described by time-dependent nonlinear partial differential equations (PDEs).
A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks
The Universal Trigger (UniTrigger) is a recently-proposed powerful adversarial textual attack method.
SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher
Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the models from scratch.
Two-stage Training of Graph Neural Networks for Graph Classification
By adapting five GNN models to our method, we demonstrate the consistent improvement in accuracy and utilization of each GNN's allocated capacity over the original training method of each model up to 5. 4\% points in 12 datasets.
MONSTOR: An Inductive Approach for Estimating and Maximizing Influence over Unseen Networks
In this work, we present an inductive machine learning method, called Monte Carlo Simulator (MONSTOR), for estimating the influence of given seed nodes in social networks unseen during training.
Solving Large-Scale 0-1 Knapsack Problems and its Application to Point Cloud Resampling
0-1 knapsack is of fundamental importance in computer science, business, operations research, etc.
Data Synthesis based on Generative Adversarial Networks
We call this property model compatibility.
Databases Cryptography and Security H.3.4; I.2; K.6.5
MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation
Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images.
MMGAN: Manifold Matching Generative Adversarial Network
MMGAN finds two manifolds representing the vector representations of real and fake images.
We used Neural Networks to Detect Clickbaits: You won't believe what happened Next!
Online content publishers often use catchy headlines for their articles in order to attract users to their websites.
