Yuya Yoshikawa

Yutaro Shigeto, Masashi Shimbo, Yuya Yoshikawa et al.

Barlow Twins and VICReg are self-supervised representation learning models that use regularizers to decorrelate features. Although these models are as effective as conventional representation learning models, their training can be computationally demanding if the dimension d of the projected embeddings is high. As the regularizers are defined in terms of individual elements of a cross-correlation or covariance matrix, computing the loss for n samples takes O(n d^2) time. In this paper, we propose a relaxed decorrelating regularizer that can be computed in O(n d log d) time by Fast Fourier Transform. We also propose an inexpensive technique to mitigate undesirable local minima that develop with the relaxation. The proposed regularizer exhibits accuracy comparable to that of existing regularizers in downstream tasks, whereas their training requires less memory and is faster for large d. The source code is available.

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 the explanations, i.e., how accurately the explanations reflect the predictor's behavior. To improve the faithfulness, we propose insertion/deletion metric-aware explanation-based optimization (ID-ExpO), which optimizes differentiable predictors to improve both the insertion and deletion scores of the explanations while maintaining their predictive accuracy. Because the original insertion and deletion metrics are non-differentiable with respect to the explanations and directly unavailable for gradient-based optimization, we extend the metrics so that they are differentiable and use them to formalize insertion and deletion metric-based regularizers. Our experimental results on image and tabular datasets show that the deep neural network-based predictors that are fine-tuned using ID-ExpO enable popular post-hoc explainers to produce more faithful and easier-to-interpret explanations while maintaining high predictive accuracy. The code is available at https://github.com/yuyay/idexpo.

Yuya Yoshikawa, Yutaro Shigeto, Masashi Shimbo et al.

The Meta Video Dataset (MetaVD) provides annotated relations between action classes in major datasets for human action recognition in videos. Although these annotated relations enable dataset augmentation, it is only applicable to those covered by MetaVD. For an external dataset to enjoy the same benefit, the relations between its action classes and those in MetaVD need to be determined. To address this issue, we consider two new machine learning tasks: action class relation detection and classification. We propose a unified model to predict relations between action classes, using language and visual information associated with classes. Experimental results show that (i) pre-trained recent neural network models for texts and videos contribute to high predictive performance, (ii) the relation prediction based on action label texts is more accurate than based on videos, and (iii) a blending approach that combines predictions by both modalities can further improve the predictive performance in some cases.

Ryotaro Shimizu, Takashi Wada, Yu Wang et al.

Recent research on explainable recommendation generally frames the task as a standard text generation problem, and evaluates models simply based on the textual similarity between the predicted and ground-truth explanations. However, this approach fails to consider one crucial aspect of the systems: whether their outputs accurately reflect the users' (post-purchase) sentiments, i.e., whether and why they would like and/or dislike the recommended items. To shed light on this issue, we introduce new datasets and evaluation methods that focus on the users' sentiments. Specifically, we construct the datasets by explicitly extracting users' positive and negative opinions from their post-purchase reviews using an LLM, and propose to evaluate systems based on whether the generated explanations 1) align well with the users' sentiments, and 2) accurately identify both positive and negative opinions of users on the target items. We benchmark several recent models on our datasets and demonstrate that achieving strong performance on existing metrics does not ensure that the generated explanations align well with the users' sentiments. Lastly, we find that existing models can provide more sentiment-aware explanations when the users' (predicted) ratings for the target items are directly fed into the models as input. The datasets and benchmark implementation are available at: https://github.com/jchanxtarov/sent_xrec.

Yuya Yoshikawa, Tomoharu Iwata, Hiroshi Sawada

Social Coding Sites (SCSs) are social media services for sharing software development projects on the Web, and many open source projects are currently being developed on SCSs. One of the characteristics of SCSs is that they provide a platform on social networks that encourages collaboration between developers with the same interests and purpose. For example, external developers can easily report bugs and improvements to the project members. In this paper, we investigate keys to the success of projects on SCSs based on large data consisting of more than three hundred thousand projects. We focus on the following three perspectives: 1) the team structure, 2) social activity with external developers, and 3) content developed by the project. To evaluate the success quantitatively, we define activity, popularity and sociality as success indexes. A summary of the findings we obtained by using the techniques of correlation analysis, social network analysis and topic extraction is as follows: the number of project members and the connectivity between the members are positively correlated with success indexes. Second, projects that faithfully tackle change requests from external developers are more likely to be successful. Third, the success indexes differ between topics of softwares developed by projects. Our analysis suggests how to be successful in various projects, not limited to social coding.

Yuya Yoshikawa, Ryotaro Shimizu, Takahiro Kawashima et al.

In scenarios requiring both prediction and explanation efficiency for image classification, self-explaining models that perform both tasks in a single inference are effective. However, their training incurs substantial labeling and computational costs. This study aims to tackle the issue by proposing a method to transfer the visual explainability of self-explaining models, learned in a source domain, to a target domain based on a task arithmetic framework. Specifically, we construct a self-explaining model by extending image classifiers based on a vision-language pretrained model. We then define an \emph{explainability vector} as the difference between model parameters trained on the source domain with and without explanation supervision. Based on the task arithmetic framework, we impart explainability to a model trained only on the prediction task in the target domain by applying the explainability vector. Experimental results on various image classification datasets demonstrate that, except for transfers between some less-related domains, visual explainability can be successfully transferred from source to target domains, improving explanation quality in the target domain without sacrificing classification accuracy. Furthermore, we show that the explainability vector learned on a large and diverse dataset like ImageNet, extended with explanation supervision, exhibits universality and robustness, improving explanation quality on nine out of ten different target datasets. We also find that the explanation quality achieved with a single model inference is comparable to that of Kernel SHAP, which requires 150 model inferences.

Yuya Yoshikawa, Masanari Kimura, Ryotaro Shimizu et al.

Techniques that explain the predictions of black-box machine learning models are crucial to make the models transparent, thereby increasing trust in AI systems. The input features to the models often have a nested structure that consists of high- and low-level features, and each high-level feature is decomposed into multiple low-level features. For such inputs, both high-level feature attributions (HiFAs) and low-level feature attributions (LoFAs) are important for better understanding the model's decision. In this paper, we propose a model-agnostic local explanation method that effectively exploits the nested structure of the input to estimate the two-level feature attributions simultaneously. A key idea of the proposed method is to introduce the consistency property that should exist between the HiFAs and LoFAs, thereby bridging the separate optimization problems for estimating them. Thanks to this consistency property, the proposed method can produce HiFAs and LoFAs that are both faithful to the black-box models and consistent with each other, using a smaller number of queries to the models. In experiments on image classification in multiple instance learning and text classification using language models, we demonstrate that the HiFAs and LoFAs estimated by the proposed method are accurate, faithful to the behaviors of the black-box models, and provide consistent explanations.

Tomoharu Iwata, Yuya Yoshikawa

Although deep models achieve high predictive performance, it is difficult for humans to understand the predictions they made. Explainability is important for real-world applications to justify their reliability. Many example-based explanation methods have been proposed, such as representer point selection, where an explanation model defined by a set of training examples is used for explaining a prediction model. For improving the interpretability, reducing the number of examples in the explanation model is important. However, the explanations with fewer examples can be unfaithful since it is difficult to approximate prediction models well by such example-based explanation models. The unfaithful explanations mean that the predictions by the explainable model are different from those by the prediction model. We propose a method for training deep models such that their predictions are faithfully explained by explanation models with a small number of examples. We train the prediction and explanation models simultaneously with a sparse regularizer for reducing the number of examples. The proposed method can be incorporated into any neural network-based prediction models. Experiments using several datasets demonstrate that the proposed method improves faithfulness while keeping the predictive performance.

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 structures via kernels, GPR has been successfully used in various applications. However, in GPR, how the features of an input contribute to its prediction cannot be interpreted. Herein, we propose GPR with local explanation, which reveals the feature contributions to the prediction of each sample, while maintaining the predictive performance of GPR. In the proposed model, both the prediction and explanation for each sample are performed using an easy-to-interpret locally linear model. The weight vector of the locally linear model is assumed to be generated from multivariate Gaussian process priors. The hyperparameters of the proposed models are estimated by maximizing the marginal likelihood. For a new test sample, the proposed model can predict the values of its target variable and weight vector, as well as their uncertainties, in a closed form. Experimental results on various benchmark datasets verify that the proposed model can achieve predictive performance comparable to those of GPR and superior to that of existing interpretable models, and can achieve higher interpretability than them, both quantitatively and qualitatively.

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 predictions, although it is difficult to interpret why such predictions are obtained by DNNs. On the other hand, interpretation of linear models is easy, although their predictive performance would be low since real-world data is often intrinsically non-linear. To combine both the benefits of the high predictive performance of DNNs and high interpretability of linear models into a single model, we propose neural generators of sparse local linear models (NGSLLs). The sparse local linear models have high flexibility as they can approximate non-linear functions. The NGSLL generates sparse linear weights for each sample using DNNs that take original representations of each sample (e.g., word sequence) and their simplified representations (e.g., bag-of-words) as input. By extracting features from the original representations, the weights can contain rich information to achieve high predictive performance. Additionally, the prediction is interpretable because it is obtained by the inner product between the simplified representations and the sparse weights, where only a small number of weights are selected by our gate module in the NGSLL. In experiments with real-world datasets, we demonstrate the effectiveness of the NGSLL quantitatively and qualitatively by evaluating prediction performance and visualizing generated weights on image and text classification tasks.

Yutaro Shigeto, Yuya Yoshikawa, Jiaqing Lin et al.

In recent years, automatic video caption generation has attracted considerable attention. This paper focuses on the generation of Japanese captions for describing human actions. While most currently available video caption datasets have been constructed for English, there is no equivalent Japanese dataset. To address this, we constructed a large-scale Japanese video caption dataset consisting of 79,822 videos and 399,233 captions. Each caption in our dataset describes a video in the form of "who does what and where." To describe human actions, it is important to identify the details of a person, place, and action. Indeed, when we describe human actions, we usually mention the scene, person, and action. In our experiments, we evaluated two caption generation methods to obtain benchmark results. Further, we investigated whether those generation methods could specify "who does what and where."

Yuya Yoshikawa, Jiaqing Lin, Akikazu Takeuchi

A new large-scale video dataset for human action recognition, called STAIR Actions is introduced. STAIR Actions contains 100 categories of action labels representing fine-grained everyday home actions so that it can be applied to research in various home tasks such as nursing, caring, and security. In STAIR Actions, each video has a single action label. Moreover, for each action category, there are around 1,000 videos that were obtained from YouTube or produced by crowdsource workers. The duration of each video is mostly five to six seconds. The total number of videos is 102,462. We explain how we constructed STAIR Actions and show the characteristics of STAIR Actions compared to existing datasets for human action recognition. Experiments with three major models for action recognition show that STAIR Actions can train large models and achieve good performance. STAIR Actions can be downloaded from http://actions.stair.center

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) is important when measuring the effects of ads shown to users and to understanding the interests of the users. There is generally a time delay (i.e., so-called {\it delayed feedback}) between the ad click and conversion. Owing to the delayed feedback, samples that are converted after an observation period may be treated as negative. To overcome this drawback, CVR prediction assuming that the time delay follows an exponential distribution has been proposed. In practice, however, there is no guarantee that the delay is generated from the exponential distribution, and the best distribution with which to represent the delay depends on the data. In this paper, we propose a nonparametric delayed feedback model for CVR prediction that represents the distribution of the time delay without assuming a parametric distribution, such as an exponential or Weibull distribution. Because the distribution of the time delay is modeled depending on the content of an ad and the features of a user, various shapes of the distribution can be represented potentially. In experiments, we show that the proposed model can capture the distribution for the time delay on a synthetic dataset, even when the distribution is complicated. Moreover, on a real dataset, we show that the proposed model outperforms the existing method that assumes an exponential distribution for the time delay in terms of conversion rate prediction.

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 belongs to at least one group. Then, instead of the true label of each instance, we observe the label distribution of the instances associated with a group, where the label distribution is distorted by an unknown noise. Our goals are to (1) estimate the true label of each instance, and (2) learn a classifier that predicts the true label of a new instance. We propose a probabilistic model that considers true label distributions of groups and parameters that represent the noise as hidden variables. The model can be learned based on a variational Bayesian method. In numerical experiments, we show that the proposed model outperforms existing methods in terms of the estimation of the true labels of instances.

Yuya Yoshikawa, Yutaro Shigeto, Akikazu Takeuchi

In recent years, automatic generation of image descriptions (captions), that is, image captioning, has attracted a great deal of attention. In this paper, we particularly consider generating Japanese captions for images. Since most available caption datasets have been constructed for English language, there are few datasets for Japanese. To tackle this problem, we construct a large-scale Japanese image caption dataset based on images from MS-COCO, which is called STAIR Captions. STAIR Captions consists of 820,310 Japanese captions for 164,062 images. In the experiment, we show that a neural network trained using STAIR Captions can generate more natural and better Japanese captions, compared to those generated using English-Japanese machine translation after generating English captions.