28 citations · 101 across the 12 of their papers we have counts for
6 papers · 1 filter
Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers
Yuya Yoshikawa, Tomoharu Iwata
The quality of explanations for the predictions made by complex machine learning predictors is often measured using insertion and deletion metrics, which assess the faithfulness of…
Learning Decorrelated Representations Efficiently Using Fast Fourier Transform
Yutaro Shigeto, Masashi Shimbo, Yuya Yoshikawa +1
Barlow Twins and VICReg are self-supervised representation learning models that use regularizers to decorrelate features. Although these models are as effective as conventional rep…
Gaussian Process Regression with Local Explanation
Yuya Yoshikawa, Tomoharu Iwata
Gaussian process regression (GPR) is a fundamental model used in machine learning. Owing to its accurate prediction with uncertainty and versatility in handling various data struct…
Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability
Yuya Yoshikawa, Tomoharu Iwata
For reliability, it is important that the predictions made by machine learning methods are interpretable by human. In general, deep neural networks (DNNs) can provide accurate pred…
A Nonparametric Delayed Feedback Model for Conversion Rate Prediction
Yuya Yoshikawa, Yusaku Imai
Predicting conversion rates (CVRs) in display advertising (e.g., predicting the proportion of users who purchase an item (i.e., a conversion) after its corresponding ad is clicked)…
Learning from Noisy Label Distributions
Yuya Yoshikawa
In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector bel…