16 citations · 52 across the 22 of their papers we have counts for
23 papers
Partial AUC Maximization from Positive-unlabeled Data
Atsutoshi Kumagai, Tomoharu Iwata, Taishi Nishiyama +3
The partial area under the receiver operating characteristic curve (pAUC) is an important performance metric for binary classification that summarizes true positive rates within a…
Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift
Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +3
Unlabeled-unlabeled (UU) learning allows us to learn a binary classifier from two sets of unlabeled data with different class-priors. It is a general framework because it includes…
AUC Maximization from Biased Positive-unlabeled Data with Confidence
Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +3
Maximizing the area under the receiver operating characteristic curve (AUC) is a standard approach to imbalanced binary classification. Although positive and negative data are requ…
Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +4
Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models su…
Meta-learning Representations for Learning from Multiple Annotators
Atsutoshi Kumagai, Tomoharu Iwata, Taishi Nishiyama +2
We propose a meta-learning method for learning from multiple noisy annotators. In many applications such as crowdsourcing services, labels for supervised learning are given by mult…
Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +2
Diffusion models are powerful generative models but often generate sensitive data that are unwanted by users, mainly because the unlabeled training data frequently contain such sen…
Meta-learning for Positive-unlabeled Classification
Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara
We propose a meta-learning method for positive and unlabeled (PU) classification, which improves the performance of binary classifiers obtained from only PU data in unseen target t…
Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +1
Semi-supervised anomaly detection, which aims to improve the anomaly detection performance by using a small amount of labeled anomaly data in addition to unlabeled data, has attrac…
Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation
Tomoharu Iwata, Atsutoshi Kumagai
Although Gaussian processes (GPs) with deep kernels have been successfully used for meta-learning in regression tasks, its uncertainty estimation performance can be poor. We propos…
Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces
Tomoharu Iwata, Atsutoshi Kumagai
We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning metho…
Regularizing Neural Networks with Meta-Learning Generative Models
Shin'ya Yamaguchi, Daiki Chijiwa, Sekitoshi Kanai +2
This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative mo…
Fast Regularized Discrete Optimal Transport with Group-Sparse Regularizers
Yasutoshi Ida, Sekitoshi Kanai, Kazuki Adachi +2
Regularized discrete optimal transport (OT) is a powerful tool to measure the distance between two discrete distributions that have been constructed from data samples on two differ…
Meta-learning for Out-of-Distribution Detection via Density Estimation in Latent Space
Tomoharu Iwata, Atsutoshi Kumagai
Many neural network-based out-of-distribution (OoD) detection methods have been proposed. However, they require many training data for each target task. We propose a simple yet eff…
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
Daiki Chijiwa, Shin'ya Yamaguchi, Atsutoshi Kumagai +1
Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized…
Transfer Learning with Pre-trained Conditional Generative Models
Shin'ya Yamaguchi, Sekitoshi Kanai, Atsutoshi Kumagai +2
Transfer learning is crucial in training deep neural networks on new target tasks. Current transfer learning methods always assume at least one of (i) source and target task label…
Recurrent Neural Networks for Learning Long-term Temporal Dependencies with Reanalysis of Time Scale Representation
Kentaro Ohno, Atsutoshi Kumagai
Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to contr…
Few-shot Learning for Unsupervised Feature Selection
Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara
We propose a few-shot learning method for unsupervised feature selection, which is a task to select a subset of relevant features in unlabeled data. Existing methods usually requir…
Meta-Learning for Relative Density-Ratio Estimation
Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara
The ratio of two probability densities, called a density-ratio, is a vital quantity in machine learning. In particular, a relative density-ratio, which is a bounded extension of th…
Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
Tomoharu Iwata, Atsutoshi Kumagai
Neural network-based anomaly detection methods have shown to achieve high performance. However, they require a large amount of training data for each task. We propose a neural netw…
Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression
Masanori Yamada, Sekitoshi Kanai, Tomoharu Iwata +4
Adversarial training is actively studied for learning robust models against adversarial examples. A recent study finds that adversarially trained models degenerate generalization p…
Few-shot Learning for Time-series Forecasting
Tomoharu Iwata, Atsutoshi Kumagai
Time-series forecasting is important for many applications. Forecasting models are usually trained using time-series data in a specific target task. However, sufficient data in the…
Semi-supervised Anomaly Detection on Attributed Graphs
Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara
We propose a simple yet effective method for detecting anomalous instances on an attribute graph with label information of a small number of instances. Although with standard anoma…
Zero-shot Domain Adaptation without Domain Semantic Descriptors
Atsutoshi Kumagai, Tomoharu Iwata
We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors.…