Author name cluster

Masahito Kurihara

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

JMLR Journal 2021 Journal Article

Factorization Machines with Regularization for Sparse Feature Interactions

Kyohei Atarashi
Satoshi Oyama
Masahito Kurihara

Factorization machines (FMs) are machine learning predictive models based on second-order feature interactions and FMs with sparse regularization are called sparse FMs. Such regularizations enable feature selection, which selects the most relevant features for accurate prediction, and therefore they can contribute to the improvement of the model accuracy and interpretability. However, because FMs use second-order feature interactions, the selection of features often causes the loss of many relevant feature interactions in the resultant models. In such cases, FMs with regularization specially designed for feature interaction selection trying to achieve interaction-level sparsity may be preferred instead of those just for feature selection trying to achieve feature-level sparsity. In this paper, we present a new regularization scheme for feature interaction selection in FMs. For feature interaction selection, our proposed regularizer makes the feature interaction matrix sparse without a restriction on sparsity patterns imposed by the existing methods. We also describe efficient proximal algorithms for the proposed FMs and how our ideas can be applied or extended to feature selection and other related models such as higher-order FMs and the all-subsets model. The analysis and experimental results on synthetic and real-world datasets show the effectiveness of the proposed methods. [abs] [ pdf ][ bib ] &copy JMLR 2021. ( edit, beta )

PDF Details

IJCAI Conference 2020 Conference Paper

Generating Natural Counterfactual Visual Explanations

Wenqi Zhao
Satoshi Oyama
Masahito Kurihara

Counterfactual explanations help users to understand the behaviors of machine learning models by changing the inputs for the existing outputs. For an image classification task, an example counterfactual visual explanation explains: "for an example that belongs to class A, what changes do we need to make to the input so that the output is more inclined to class B. " Our research considers changing the attribute description text of class A on the basis of the attributes of class B and generating counterfactual images on the basis of the modified text. We can use the prediction results of the model on counterfactual images to find the attributes that have the greatest effect when the model is predicting classes A and B. We applied our method to a fine-grained image classification dataset and used the generative adversarial network to generate natural counterfactual visual explanations. To evaluate these explanations, we used them to assist crowdsourcing workers in an image classification task. We found that, within a specific range, they improved classification accuracy.

PDF Details DOI

AAAI Conference 2018 Conference Paper

Semi-Supervised Learning From Crowds Using Deep Generative Models

Kyohei Atarashi
Satoshi Oyama
Masahito Kurihara

Although supervised learning requires a labeled dataset, obtaining labels from experts is generally expensive. For this reason, crowdsourcing services are attracting attention in the ﬁeld of machine learning as a way to collect labels at relatively low cost. However, the labels obtained by crowdsourcing, i. e. , from non-expert workers, are often noisy. A number of methods have thus been devised for inferring true labels, and several methods have been proposed for learning classiﬁers directly from crowdsourced labels, referred to as learning from crowds. A more practical problem is learning from crowdsourced labeled data and unlabeled data, i. e. , semi-supervised learning from crowds. This paper presents a novel generative model of the labeling process in crowdsourcing. It leverages unlabeled data effectively by introducing latent features and a data distribution. Because the data distribution can be complicated, we use a deep neural network for the data distribution. Therefore, our model can be regarded as a kind of deep generative model. The problems caused by the intractability of latent variable posteriors is solved by introducing an inference model. The experiments show that it outperforms four existing models, including a baseline model, on the MNIST dataset with simulated workers and the Rotten Tomatoes movie review dataset with Amazon Mechanical Turk workers.

PDF Details

IJCAI Conference 2015 Conference Paper

Crowdsourced Semantic Matching of Multi-Label Annotations

Lei Duan
Satoshi Oyama
Masahito Kurihara
Haruhiko Sato

Most multi-label domains lack an authoritative taxonomy. Therefore, different taxonomies are commonly used in the same domain, which results in complications. Although this situation occurs frequently, there has been little study of it using a principled statistical approach. Given that (1) different taxonomies used in the same domain are generally founded on the same latent semantic space, where each possible label set in a taxonomy denotes a single semantic concept, and that (2) crowdsourcing is beneficial in identifying relationships between semantic concepts and instances at low cost, we proposed a novel probabilistic cascaded method for establishing a semantic matching function in a crowdsourcing setting that maps label sets in one (source) taxonomy to label sets in another (target) taxonomy in terms of the semantic distances between them. The established function can be used to detect the associated label set in the target taxonomy for an instance directly from its associated label set in the source taxonomy without any extra effort. Experimental results on real-world data (emotion annotations for narrative sentences) demonstrated that the proposed method can robustly establish semantic matching functions exhibiting satisfactory performance from a limited number of crowdsourced annotations.

PDF Details

TCS Journal 1995 Journal Article

Modularity in noncopying term rewriting

Masahito Kurihara
Azuma Ohuchi

It is known that termination and completeness are not modular properties of term rewriting systems: the disjoint union of terminating (complete) term rewriting systems need not be terminating (complete). In this paper, we introduce a class of “noncopying” term rewriting systems as a new, term-based formalism for a kind of graph rewriting systems, and prove that this class enjoys the modularity of termination and of completeness. Actually, our results are stronger in the sense that the disjointness condition is relaxed for allowing the systems to share constructors and some defined symbols while preserving the main results.

Details DOI

TCS Journal 1992 Journal Article

Modularity of simple termination of term rewriting systems with shared constructors

Masahito Kurihara
Azuma Ohuchi

A term rewriting system is simply terminating if there exists a simplification ordering showing its termination. Let R 0 and R 1 be term rewriting systems which share no defined symbol (but may share constructors). Constructors are function symbols which do not occur at the leftmost position in left-hand sides of rewrite rules; the rest of the function symbols are defined symbols. In this paper, we prove that R 0⌣R 1 is simply terminating if and only if both R 0 and R 1 are so.

Details DOI