185 citations · 419 across the 15 of their papers we have counts for
15 papers
Virtual Human Generative Model: Masked Modeling Approach for Learning Human Characteristics
Kenta Oono, Nontawat Charoenphakdee, Kotatsu Bito +14
Virtual Human Generative Model (VHGM) is a generative model that approximates the joint probability over more than 2000 human healthcare-related attributes. This paper presents the…
TabRet: Pre-training Transformer-based Tabular Models for Unseen Columns
Soma Onishi, Kenta Oono, Kohei Hayashi
We present \emph{TabRet}, a pre-trainable Transformer-based model for tabular data. TabRet is designed to work on a downstream task that contains columns not seen in pre-training.…
Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
Yuri Kinoshita, Kenta Oono, Kenji Fukumizu +2
Variational autoencoders (VAEs) are one of the deep generative models that have experienced enormous success over the past decades. However, in practice, they suffer from a problem…
Universal approximation property of invertible neural networks
Isao Ishikawa, Takeshi Teshima, Koichi Tojo +3
Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various m…
Fast Estimation Method for the Stability of Ensemble Feature Selectors
Rina Onda, Zhengyan Gao, Masaaki Kotera +1
It is preferred that feature selectors be \textit{stable} for better interpretabity and robust prediction. Ensembling is known to be effective for improving the stability of featur…
Universal Approximation Property of Neural Ordinary Differential Equations
Takeshi Teshima, Koichi Tojo, Masahiro Ikeda +2
Neural ordinary differential equations (NODEs) is an invertible neural network architecture promising for its free-form Jacobian and the availability of a tractable Jacobian determ…
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
Takeshi Teshima, Isao Ishikawa, Koichi Tojo +3
Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirabl…
Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
Kenta Oono, Taiji Suzuki
It is known that the current graph neural networks (GNNs) are difficult to make themselves deep due to the problem known as over-smoothing. Multi-scale GNNs are a promising approac…
Weisfeiler-Lehman Embedding for Molecular Graph Neural Networks
Katsuhiko Ishiguro, Kenta Oono, Kohei Hayashi
A graph neural network (GNN) is a good choice for predicting the chemical properties of molecules. Compared with other deep networks, however, the current performance of a GNN is l…
Graph Residual Flow for Molecular Graph Generation
Shion Honda, Hirotaka Akita, Katsuhiko Ishiguro +2
Statistical generative models for molecular graphs attract attention from many researchers from the fields of bio- and chemo-informatics. Among these models, invertible flow-based…
Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
Kenta Oono, Taiji Suzuki
Graph Neural Networks (graph NNs) are a promising deep learning approach for analyzing graph-structured data. However, it is known that they do not improve (or sometimes worsen) th…
Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks
Kenta Oono, Taiji Suzuki
Convolutional neural networks (CNNs) have been shown to achieve optimal approximation and estimation error rates (in minimax sense) in several function classes. However, previous a…
Population-based de novo molecule generation, using grammatical evolution
Naruki Yoshikawa, Kei Terayama, Teruki Honma +2
Automatic design with machine learning and molecular simulations has shown a remarkable ability to generate new and promising drug candidates. Current models, however, still have p…
Semi-supervised learning of hierarchical representations of molecules using neural message passing
Hai Nguyen, Shin-ichi Maeda, Kenta Oono
With the rapid increase of compound databases available in medicinal and material science, there is a growing need for learning representations of molecules in a semi-supervised ma…
Testing Properties of Functions on Finite Groups
Kenta Oono, Yuichi Yoshida
We study testing properties of functions on finite groups. First we consider functions of the form , where is a finite group. We show that conjugate invaria…