Tomoharu Iwata

Maya Okawa, Tomoharu Iwata

Opinion formation and propagation are crucial phenomena in social networks and have been extensively studied across several disciplines. Traditionally, theoretical models of opinion dynamics have been proposed to describe the interactions between individuals (i.e., social interaction) and their impact on the evolution of collective opinions. Although these models can incorporate sociological and psychological knowledge on the mechanisms of social interaction, they demand extensive calibration with real data to make reliable predictions, requiring much time and effort. Recently, the widespread use of social media platforms provides new paradigms to learn deep learning models from a large volume of social media data. However, these methods ignore any scientific knowledge about the mechanism of social interaction. In this work, we present the first hybrid method called Sociologically-Informed Neural Network (SINN), which integrates theoretical models and social media data by transporting the concepts of physics-informed neural networks (PINNs) from natural science (i.e., physics) into social science (i.e., sociology and social psychology). In particular, we recast theoretical models as ordinary differential equations (ODEs). Then we train a neural network that simultaneously approximates the data and conforms to the ODEs that represent the social scientific knowledge. In addition, we extend PINNs by integrating matrix factorization and a language model to incorporate rich side information (e.g., user profiles) and structural knowledge (e.g., cluster structure of the social interaction network). Moreover, we develop an end-to-end training procedure for SINN, which involves Gumbel-Softmax approximation to include stochastic mechanisms of social interaction. Extensive experiments on real-world and synthetic datasets show SINN outperforms six baseline methods in predicting opinion dynamics.

Futoshi Futami, Tomoharu Iwata, Naonori Ueda et al.

Bayesian deep learning plays an important role especially for its ability evaluating epistemic uncertainty (EU). Due to computational complexity issues, approximation methods such as variational inference (VI) have been used in practice to obtain posterior distributions and their generalization abilities have been analyzed extensively, for example, by PAC-Bayesian theory; however, little analysis exists on EU, although many numerical experiments have been conducted on it. In this study, we analyze the EU of supervised learning in approximate Bayesian inference by focusing on its excess risk. First, we theoretically show the novel relations between generalization error and the widely used EU measurements, such as the variance and mutual information of predictive distribution, and derive their convergence behaviors. Next, we clarify how the objective function of VI regularizes the EU. With this analysis, we propose a new objective function for VI that directly controls the prediction performance and the EU based on the PAC-Bayesian theory. Numerical experiments show that our algorithm significantly improves the EU evaluation over the existing VI methods.

Tomoharu Iwata, Yusuke Tanaka, Naonori Ueda

We propose a neural network-based meta-learning method to efficiently solve partial differential equation (PDE) problems. The proposed method is designed to meta-learn how to solve a wide variety of PDE problems, and uses the knowledge for solving newly given PDE problems. We encode a PDE problem into a problem representation using neural networks, where governing equations are represented by coefficients of a polynomial function of partial derivatives, and boundary conditions are represented by a set of point-condition pairs. We use the problem representation as an input of a neural network for predicting solutions, which enables us to efficiently predict problem-specific solutions by the forwarding process of the neural network without updating model parameters. To train our model, we minimize the expected error when adapted to a PDE problem based on the physics-informed neural network framework, by which we can evaluate the error even when solutions are unknown. We demonstrate that our proposed method outperforms existing methods in predicting solutions of PDE problems.

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.

Futoshi Futami, Tomoharu Iwata

Bayesian inference is often utilized for uncertainty quantification tasks. A recent analysis by Xu and Raginsky 2022 rigorously decomposed the predictive uncertainty in Bayesian inference into two uncertainties, called aleatoric and epistemic uncertainties, which represent the inherent randomness in the data-generating process and the variability due to insufficient data, respectively. They analyzed those uncertainties in an information-theoretic way, assuming that the model is well-specified and treating the model's parameters as latent variables. However, the existing information-theoretic analysis of uncertainty cannot explain the widely believed property of uncertainty, known as the sensitivity between the test and training data. It implies that when test data are similar to training data in some sense, the epistemic uncertainty should become small. In this work, we study such uncertainty sensitivity using our novel decomposition method for the predictive uncertainty. Our analysis successfully defines such sensitivity using information-theoretic quantities. Furthermore, we extend the existing analysis of Bayesian meta-learning and show the novel sensitivities among tasks for the first time.

Tomoharu Iwata, Yoshinobu Kawahara

We propose a data-driven method for controlling the frequency and convergence rate of black-box nonlinear dynamical systems based on the Koopman operator theory. With the proposed method, a policy network is trained such that the eigenvalues of a Koopman operator of controlled dynamics are close to the target eigenvalues. The policy network consists of a neural network to find a Koopman invariant subspace, and a pole placement module to adjust the eigenvalues of the Koopman operator. Since the policy network is differentiable, we can train it in an end-to-end fashion using reinforcement learning. We demonstrate that the proposed method achieves better performance than model-free reinforcement learning and model-based control with system identification.

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 methods assume that all tasks share the same attribute space, which prevents us from learning with a wide variety of tasks. With the proposed method, the expected test performance on tasks with a small amount of labeled data is improved with unlabeled data as well as data in various tasks, where the attribute spaces are different among tasks. The proposed method embeds labeled and unlabeled data simultaneously in a task-specific space using a neural network, and the unlabeled data's labels are estimated by adapting classification or regression models in the embedding space. For the neural network, we develop variable-feature self-attention layers, which enable us to find embeddings of data with different attribute spaces with a single neural network by considering interactions among examples, attributes, and labels. Our experiments on classification and regression datasets with heterogeneous attribute spaces demonstrate that our proposed method outperforms the existing meta-learning and semi-supervised learning methods.

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 effective meta-learning method to detect OoD with small in-distribution data in a target task. With the proposed method, the OoD detection is performed by density estimation in a latent space. A neural network shared among all tasks is used to flexibly map instances in the original space to the latent space. The neural network is meta-learned such that the expected OoD detection performance is improved by using various tasks that are different from the target tasks. This meta-learning procedure enables us to obtain appropriate representations in the latent space for OoD detection. For density estimation, we use a Gaussian mixture model (GMM) with full covariance for each class. We can adapt the GMM parameters to in-distribution data in each task in a closed form by maximizing the likelihood. Since the closed form solution is differentiable, we can meta-learn the neural network efficiently with a stochastic gradient descent method by incorporating the solution into the meta-learning objective function. In experiments using six datasets, we demonstrate that the proposed method achieves better performance than existing meta-learning and OoD detection methods.

Shuhei A. Horiguchi, Tomoharu Iwata, Taku Tsuzuki et al.

The optimization of high-dimensional black-box functions is a challenging problem. When a low-dimensional linear embedding structure can be assumed, existing Bayesian optimization (BO) methods often transform the original problem into optimization in a low-dimensional space. They exploit the low-dimensional structure and reduce the computational burden. However, we reveal that this approach could be limited or inefficient in exploring the high-dimensional space mainly due to the biased reconstruction of the high-dimensional queries from the low-dimensional queries. In this paper, we investigate a simple alternative approach: tackling the problem in the original high-dimensional space using the information from the learned low-dimensional structure. We provide a theoretical analysis of the exploration ability. Furthermore, we show that our method is applicable to batch optimization problems with thousands of dimensions without any computational difficulty. We demonstrate the effectiveness of our method on high-dimensional benchmarks and a real-world function.

Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata et al.

Aggregate data often appear in various fields such as socio-economics and public security. The aggregate data are associated not with points but with supports (e.g., spatial regions in a city). Since the supports may have various granularities depending on attributes (e.g., poverty rate and crime rate), modeling such data is not straightforward. This article offers a multi-output Gaussian process (MoGP) model that infers functions for attributes using multiple aggregate datasets of respective granularities. In the proposed model, the function for each attribute is assumed to be a dependent GP modeled as a linear mixing of independent latent GPs. We design an observation model with an aggregation process for each attribute; the process is an integral of the GP over the corresponding support. We also introduce a prior distribution of the mixing weights, which allows a knowledge transfer across domains (e.g., cities) by sharing the prior. This is advantageous in such a situation where the spatially aggregated dataset in a city is too coarse to interpolate; the proposed model can still make accurate predictions of attributes by utilizing aggregate datasets in other cities. The inference of the proposed model is based on variational Bayes, which enables one to learn the model parameters using the aggregate datasets from multiple domains. The experiments demonstrate that the proposed model outperforms in the task of refining coarse-grained aggregate data on real-world datasets: Time series of air pollutants in Beijing and various kinds of spatial datasets from New York City and Chicago.

Tomoharu Iwata, Yoshinobu Kawahara

We propose a neural network-based model for nonlinear dynamics in continuous time that can impose inductive biases on decay rates and/or frequencies. Inductive biases are helpful for training neural networks especially when training data are small. The proposed model is based on the Koopman operator theory, where the decay rate and frequency information is used by restricting the eigenvalues of the Koopman operator that describe linear evolution in a Koopman space. We use neural networks to find an appropriate Koopman space, which are trained by minimizing multi-step forecasting and backcasting errors using irregularly sampled time-series data. Experiments on various time-series datasets demonstrate that the proposed method achieves higher forecasting performance given a single short training sequence than the existing methods.

Tomoharu Iwata

Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed over multiple instances in a set in some real-world applications. To reduce the labeling cost for training regression models for such aggregated data, we propose an active learning method that sequentially selects sets to be labeled to improve the predictive performance with fewer labeled sets. For the selection measurement, the proposed method uses the mutual information, which quantifies the reduction of the uncertainty of the model parameters by observing the aggregated output. With Bayesian linear basis functions for modeling outputs given an input, which include approximated Gaussian processes and neural networks, we can efficiently calculate the mutual information in a closed form. With the experiments using various datasets, we demonstrate that the proposed method achieves better predictive performance with fewer labeled sets than existing methods.

Yuka Hashimoto, Tomoharu Iwata

Physics-Informed Neural Networks (PINNs) and their variational counterparts (VPINNs) are neural networks that incorporate physical laws, making them useful for scientific problems. Existing generalization analyses for PINNs and VPINNs remain limited, often requiring restrictive assumptions such as stability conditions or linear ellipticity. In this paper, we derive generalization bounds for neural networks that involve differentiation with respect to input variables, covering PINNs and VPINNs under a unified framework. We apply Taylor expansion to represent nonlinear differential operators as linear operators on a high-dimensional space, enabling the use of Koopman-based analysis and showing that high-rank networks can generalize well even in settings involving differential operators. We also show that the nonlinearity of the differential operator exponentially enlarges the bound, highlighting its significant impact on generalization.

Tomoharu Iwata, Futoshi Futami

We propose a data-driven framework for efficiently solving quadratic programming (QP) problems by reducing the number of variables in high-dimensional QPs using instance-specific projection. A graph neural network-based model is designed to generate projections tailored to each QP instance, enabling us to produce high-quality solutions even for previously unseen problems. The model is trained on heterogeneous QPs to minimize the expected objective value evaluated on the projected solutions. This is formulated as a bilevel optimization problem; the inner optimization solves the QP under a given projection using a QP solver, while the outer optimization updates the model parameters. We develop an efficient algorithm to solve this bilevel optimization problem, which computes parameter gradients without backpropagating through the solver. We provide a theoretical analysis of the generalization ability of solving QPs with projection matrices generated by neural networks. Experimental results demonstrate that our method produces high-quality feasible solutions with reduced computation time, outperforming existing methods.

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.

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 propose a meta-learning method for calibrating deep kernel GPs for improving regression uncertainty estimation performance with a limited number of training data. The proposed method meta-learns how to calibrate uncertainty using data from various tasks by minimizing the test expected calibration error, and uses the knowledge for unseen tasks. We design our model such that the adaptation and calibration for each task can be performed without iterative procedures, which enables effective meta-learning. In particular, a task-specific uncalibrated output distribution is modeled by a GP with a task-shared encoder network, and it is transformed to a calibrated one using a cumulative density function of a task-specific Gaussian mixture model (GMM). By integrating the GP and GMM into our neural network-based model, we can meta-learn model parameters in an end-to-end fashion. Our experiments demonstrate that the proposed method improves uncertainty estimation performance while keeping high regression performance compared with the existing methods using real-world datasets in few-shot settings.

Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai et al.

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 sensitive data. Since labeling all sensitive data in the large-scale unlabeled training data is impractical, we address this problem by using a small amount of labeled sensitive data. In this paper, we propose positive-unlabeled diffusion models, which prevent the generation of sensitive data using unlabeled and sensitive data. Our approach can approximate the evidence lower bound (ELBO) for normal (negative) data using only unlabeled and sensitive (positive) data. Therefore, even without labeled normal data, we can maximize the ELBO for normal data and minimize it for labeled sensitive data, ensuring the generation of only normal data. Through experiments across various datasets and settings, we demonstrated that our approach can prevent the generation of sensitive images without compromising image quality.

Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai et al.

Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models such as the Bradley-Terry model, this assumption may fail to accurately capture true human preferences, and consequently, these methods lack statistical consistency, i.e., the guarantee that language models converge to the true human preference as the number of samples increases. In contrast, direct density ratio optimization (DDRO) achieves statistical consistency without assuming any human preference models. DDRO models the density ratio between preferred and non-preferred data distributions using the language model, and then optimizes it via density ratio estimation. However, this density ratio is unstable and often diverges, leading to training instability of DDRO. In this paper, we propose a novel alignment method that is both stable and statistically consistent. Our approach is based on the relative density ratio between the preferred data distribution and a mixture of the preferred and non-preferred data distributions. Our approach is stable since this relative density ratio is bounded above and does not diverge. Moreover, it is statistically consistent and yields significantly tighter convergence guarantees than DDRO. We experimentally show its effectiveness with Qwen 2.5 and Llama 3.

Tomoya Yamashita, Yuuki Yamanaka, Masanori Yamada et al.

Machine Unlearning (MU) has recently attracted considerable attention as a solution to privacy and copyright issues in large language models (LLMs). Existing MU methods aim to remove specific target sentences from an LLM while minimizing damage to unrelated knowledge. However, these approaches require explicit target sentences and do not support removing broader concepts, such as persons or events. To address this limitation, we introduce Concept Unlearning (CU) as a new requirement for LLM unlearning. We leverage knowledge graphs to represent the LLM's internal knowledge and define CU as removing the forgetting target nodes and associated edges. This graph-based formulation enables a more intuitive unlearning and facilitates the design of more effective methods. We propose a novel method that prompts the LLM to generate knowledge triplets and explanatory sentences about the forgetting target and applies the unlearning process to these representations. Our approach enables more precise and comprehensive concept removal by aligning the unlearning process with the LLM's internal knowledge representations. Experiments on real-world and synthetic datasets demonstrate that our method effectively achieves concept-level unlearning while preserving unrelated knowledge.

Yoshiaki Takimoto, Yusuke Tanaka, Tomoharu Iwata et al.

Human activities generate various event sequences such as taxi trip records, bike-sharing pick-ups, crime occurrence, and infectious disease transmission. The point process is widely used in many applications to predict such events related to human activities. However, point processes present two problems in predicting events related to human activities. First, recent high-performance point process models require the input of sufficient numbers of events collected over a long period (i.e., long sequences) for training, which are often unavailable in realistic situations. Second, the long-term predictions required in real-world applications are difficult. To tackle these problems, we propose a novel meta-learning approach for periodicity-aware prediction of future events given short sequences. The proposed method first embeds short sequences into hidden representations (i.e., task representations) via recurrent neural networks for creating predictions from short sequences. It then models the intensity of the point process by monotonic neural networks (MNNs), with the input being the task representations. We transfer the prior knowledge learned from related tasks and can improve event prediction given short sequences of target tasks. We design the MNNs to explicitly take temporal periodic patterns into account, contributing to improved long-term prediction performance. Experiments on multiple real-world datasets demonstrate that the proposed method has higher prediction performance than existing alternatives.

Hans Jarett Ong, Yoichi Chikahara, Tomoharu Iwata

Uncovering the underlying causal mechanisms of complex real-world systems remains a significant challenge, as these systems often entail high data collection costs and involve unknown interventions. We introduce MetaCaDI, the first framework to cast the joint discovery of a causal graph and unknown interventions as a meta-learning problem. MetaCaDI is a Bayesian framework that learns a shared causal graph structure across multiple experiments and is optimized to rapidly adapt to new, few-shot intervention target prediction tasks. A key innovation is our model's analytical adaptation, which uses a closed-form solution to bypass expensive and potentially unstable gradient-based bilevel optimization. Extensive experiments on synthetic and complex gene expression data demonstrate that MetaCaDI significantly outperforms state-of-the-art methods. It excels at both causal graph recovery and identifying intervention targets from as few as 10 data instances, proving its robustness in data-scarce scenarios.

Hideaki Kim, Tomoharu Iwata

The representer theorem is a cornerstone of kernel methods, which aim to estimate latent functions in reproducing kernel Hilbert spaces (RKHSs) in a nonparametric manner. Its significance lies in converting inherently infinite-dimensional optimization problems into finite-dimensional ones over dual coefficients, thereby enabling practical and computationally tractable algorithms. In this paper, we address the problem of estimating the latent triggering kernels--functions that encode the interaction structure between events--for linear multivariate Hawkes processes based on observed event sequences within an RKHS framework. We show that, under the principle of penalized least squares minimization, a novel form of representer theorem emerges: a family of transformed kernels can be defined via a system of simultaneous integral equations, and the optimal estimator of each triggering kernel is expressed as a linear combination of these transformed kernels evaluated at the data points. Remarkably, the dual coefficients are all analytically fixed to unity, obviating the need to solve a costly optimization problem to obtain the dual coefficients. This leads to a highly efficient estimator capable of handling large-scale data more effectively than conventional nonparametric approaches. Empirical evaluations on synthetic datasets reveal that the proposed method attains competitive predictive accuracy while substantially improving computational efficiency over existing state-of-the-art kernel method-based estimators.

Atsutoshi Kumagai, Tomoharu Iwata, Taishi Nishiyama et al.

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 multiple annotators. Since the annotators have different skills or biases, given labels can be noisy. To learn accurate classifiers, existing methods require many noisy annotated data. However, sufficient data might be unavailable in practice. To overcome the lack of data, the proposed method uses labeled data obtained in different but related tasks. The proposed method embeds each example in tasks to a latent space by using a neural network and constructs a probabilistic model for learning a task-specific classifier while estimating annotators' abilities on the latent space. This neural network is meta-learned to improve the expected test classification performance when the classifier is adapted to a given small amount of annotated data. This classifier adaptation is performed by maximizing the posterior probability via the expectation-maximization (EM) algorithm. Since each step in the EM algorithm is easily computed as a closed-form and is differentiable, the proposed method can efficiently backpropagate the loss through the EM algorithm to meta-learn the neural network. We show the effectiveness of our method with real-world datasets with synthetic noise and real-world crowdsourcing datasets.

Hideaki Kim, Tomoharu Iwata, Akinori Fujino

Kernel method-based intensity estimators, formulated within reproducing kernel Hilbert spaces (RKHSs), and classical kernel intensity estimators (KIEs) have been among the most easy-to-implement and feasible methods for estimating the intensity functions of inhomogeneous Poisson processes. While both approaches share the term "kernel", they are founded on distinct theoretical principles, each with its own strengths and limitations. In this paper, we propose a novel regularized kernel method for Poisson processes based on the least squares loss and show that the resulting intensity estimator involves a specialized variant of the representer theorem: it has the dual coefficient of unity and coincides with classical KIEs. This result provides new theoretical insights into the connection between classical KIEs and kernel method-based intensity estimators, while enabling us to develop an efficient KIE by leveraging advanced techniques from RKHS theory. We refer to the proposed model as the kernel method-based kernel intensity estimator (K$^2$IE). Through experiments on synthetic datasets, we show that K$^2$IE achieves comparable predictive performance while significantly surpassing the state-of-the-art kernel method-based estimator in computational efficiency.

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 tasks. PU learning is an important problem since PU data naturally arise in real-world applications such as outlier detection and information retrieval. Existing PU learning methods require many PU data, but sufficient data are often unavailable in practice. The proposed method minimizes the test classification risk after the model is adapted to PU data by using related tasks that consist of positive, negative, and unlabeled data. We formulate the adaptation as an estimation problem of the Bayes optimal classifier, which is an optimal classifier to minimize the classification risk. The proposed method embeds each instance into a task-specific space using neural networks. With the embedded PU data, the Bayes optimal classifier is estimated through density-ratio estimation of PU densities, whose solution is obtained as a closed-form solution. The closed-form solution enables us to efficiently and effectively minimize the test classification risk. We empirically show that the proposed method outperforms existing methods with one synthetic and three real-world datasets.

Yusuke Tanaka, Takaharu Yaguchi, Tomoharu Iwata et al.

The operator learning has received significant attention in recent years, with the aim of learning a mapping between function spaces. Prior works have proposed deep neural networks (DNNs) for learning such a mapping, enabling the learning of solution operators of partial differential equations (PDEs). However, these works still struggle to learn dynamics that obeys the laws of physics. This paper proposes Energy-consistent Neural Operators (ENOs), a general framework for learning solution operators of PDEs that follows the energy conservation or dissipation law from observed solution trajectories. We introduce a novel penalty function inspired by the energy-based theory of physics for training, in which the energy functional is modeled by another DNN, allowing one to bias the outputs of the DNN-based solution operators to ensure energetic consistency without explicit PDEs. Experiments on multiple physical systems show that ENO outperforms existing DNN models in predicting solutions from data, especially in super-resolution settings.

Tomoharu Iwata, Yoichi Chikahara

This article proposes a meta-learning method for estimating the conditional average treatment effect (CATE) from a few observational data. The proposed method learns how to estimate CATEs from multiple tasks and uses the knowledge for unseen tasks. In the proposed method, based on the meta-learner framework, we decompose the CATE estimation problem into sub-problems. For each sub-problem, we formulate our estimation models using neural networks with task-shared and task-specific parameters. With our formulation, we can obtain optimal task-specific parameters in a closed form that are differentiable with respect to task-shared parameters, making it possible to perform effective meta-learning. The task-shared parameters are trained such that the expected CATE estimation performance in few-shot settings is improved by minimizing the difference between a CATE estimated with a large amount of data and one estimated with just a few data. Our experimental results demonstrate that our method outperforms the existing meta-learning approaches and CATE estimation methods.

Keisuke Kinoshita, Marc Delcroix, Tomoharu Iwata

Speaker diarization has been investigated extensively as an important central task for meeting analysis. Recent trend shows that integration of end-to-end neural (EEND)-and clustering-based diarization is a promising approach to handle realistic conversational data containing overlapped speech with an arbitrarily large number of speakers, and achieved state-of-the-art results on various tasks. However, the approaches proposed so far have not realized {\it tight} integration yet, because the clustering employed therein was not optimal in any sense for clustering the speaker embeddings estimated by the EEND module. To address this problem, this paper introduces a {\it trainable} clustering algorithm into the integration framework, by deep-unfolding a non-parametric Bayesian model called the infinite Gaussian mixture model (iGMM). Specifically, the speaker embeddings are optimized during training such that it better fits iGMM clustering, based on a novel clustering loss based on Adjusted Rand Index (ARI). Experimental results based on CALLHOME data show that the proposed approach outperforms the conventional approach in terms of diarization error rate (DER), especially by substantially reducing speaker confusion errors, that indeed reflects the effectiveness of the proposed iGMM integration.

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.

Hitoshi Shimizu, Hirohiko Suwa, Tomoharu Iwata et al.

Evacuation shelters, which are urgently required during natural disasters, are designed to minimize the burden of evacuation on human survivors. However, the larger the scale of the disaster, the more costly it becomes to operate shelters. When the number of evacuees decreases, the operation costs can be reduced by moving the remaining evacuees to other shelters and closing shelters as quickly as possible. On the other hand, relocation between shelters imposes a huge emotional burden on evacuees. In this study, we formulate the "Evacuation Shelter Scheduling Problem," which allocates evacuees to shelters in such a way to minimize the movement costs of the evacuees and the operation costs of the shelters. Since it is difficult to solve this quadratic programming problem directly, we show its transformation into a 0-1 integer programming problem. In addition, such a formulation struggles to calculate the burden of relocating them from historical data because no payments are actually made. To solve this issue, we propose a method that estimates movement costs based on the numbers of evacuees and shelters during an actual disaster. Simulation experiments with records from the Kobe earthquake (Great Hanshin-Awaji Earthquake) showed that our proposed method reduced operation costs by 33.7 million dollars: 32%.

Tomoharu Iwata

For Bayesian optimization (BO) on high-dimensional data with complex structure, neural network-based kernels for Gaussian processes (GPs) have been used to learn flexible surrogate functions by the high representation power of deep learning. However, existing methods train neural networks by maximizing the marginal likelihood, which do not directly improve the BO performance. In this paper, we propose a meta-learning method for BO with neural network-based kernels that minimizes the expected gap between the true optimum value and the best value found by BO. We model a policy, which takes the current evaluated data points as input and outputs the next data point to be evaluated, by a neural network, where neural network-based kernels, GPs, and mutual information-based acquisition functions are used as its layers. With our model, the neural network-based kernel is trained to be appropriate for the acquisition function by backpropagating the gap through the acquisition function and GP. Our model is trained by a reinforcement learning framework from multiple tasks. Since the neural network is shared across different tasks, we can gather knowledge on BO from multiple training tasks, and use the knowledge for unseen test tasks. In experiments using three text document datasets, we demonstrate that the proposed method achieves better BO performance than the existing methods.

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 require many instances for feature selection. However, sufficient instances are often unavailable in practice. The proposed method can select a subset of relevant features in a target task given a few unlabeled target instances by training with unlabeled instances in multiple source tasks. Our model consists of a feature selector and decoder. The feature selector outputs a subset of relevant features taking a few unlabeled instances as input such that the decoder can reconstruct the original features of unseen instances from the selected ones. The feature selector uses the Concrete random variables to select features via gradient descent. To encode task-specific properties from a few unlabeled instances to the model, the Concrete random variables and decoder are modeled using permutation-invariant neural networks that take a few unlabeled instances as input. Our model is trained by minimizing the expected test reconstruction error given a few unlabeled instances that is calculated with datasets in source tasks. We experimentally demonstrate that the proposed method outperforms existing feature selection methods.

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 the density-ratio, has received much attention due to its stability and has been used in various applications such as outlier detection and dataset comparison. Existing methods for (relative) density-ratio estimation (DRE) require many instances from both densities. However, sufficient instances are often unavailable in practice. In this paper, we propose a meta-learning method for relative DRE, which estimates the relative density-ratio from a few instances by using knowledge in related datasets. Specifically, given two datasets that consist of a few instances, our model extracts the datasets' information by using neural networks and uses it to obtain instance embeddings appropriate for the relative DRE. We model the relative density-ratio by a linear model on the embedded space, whose global optimum solution can be obtained as a closed-form solution. The closed-form solution enables fast and effective adaptation to a few instances, and its differentiability enables us to train our model such that the expected test error for relative DRE can be explicitly minimized after adapting to a few instances. We empirically demonstrate the effectiveness of the proposed method by using three problems: relative DRE, dataset comparison, and outlier detection.

Tomoharu Iwata

We propose a method that meta-learns a knowledge on matrix factorization from various matrices, and uses the knowledge for factorizing unseen matrices. The proposed method uses a neural network that takes a matrix as input, and generates prior distributions of factorized matrices of the given matrix. The neural network is meta-learned such that the expected imputation error is minimized when the factorized matrices are adapted to each matrix by a maximum a posteriori (MAP) estimation. We use a gradient descent method for the MAP estimation, which enables us to backpropagate the expected imputation error through the gradient descent steps for updating neural network parameters since each gradient descent step is written in a closed form and is differentiable. The proposed method can meta-learn from matrices even when their rows and columns are not shared, and their sizes are different from each other. In our experiments with three user-item rating datasets, we demonstrate that our proposed method can impute the missing values from a limited number of observations in unseen matrices after being trained with different matrices.

Futoshi Futami, Tomoharu Iwata, Naonori Ueda et al.

Bayesian model averaging, obtained as the expectation of a likelihood function by a posterior distribution, has been widely used for prediction, evaluation of uncertainty, and model selection. Various approaches have been developed to efficiently capture the information in the posterior distribution; one such approach is the optimization of a set of models simultaneously with interaction to ensure the diversity of the individual models in the same way as ensemble learning. A representative approach is particle variational inference (PVI), which uses an ensemble of models as an empirical approximation for the posterior distribution. PVI iteratively updates each model with a repulsion force to ensure the diversity of the optimized models. However, despite its promising performance, a theoretical understanding of this repulsion and its association with the generalization ability remains unclear. In this paper, we tackle this problem in light of PAC-Bayesian analysis. First, we provide a new second-order Jensen inequality, which has the repulsion term based on the loss function. Thanks to the repulsion term, it is tighter than the standard Jensen inequality. Then, we derive a novel generalization error bound and show that it can be reduced by enhancing the diversity of models. Finally, we derive a new PVI that optimizes the generalization error bound directly. Numerical experiments demonstrate that the performance of the proposed PVI compares favorably with existing methods in the experiment.

Maya Okawa, Tomoharu Iwata, Yusuke Tanaka et al.

Sequences of events including infectious disease outbreaks, social network activities, and crimes are ubiquitous and the data on such events carry essential information about the underlying diffusion processes between communities (e.g., regions, online user groups). Modeling diffusion processes and predicting future events are crucial in many applications including epidemic control, viral marketing, and predictive policing. Hawkes processes offer a central tool for modeling the diffusion processes, in which the influence from the past events is described by the triggering kernel. However, the triggering kernel parameters, which govern how each community is influenced by the past events, are assumed to be static over time. In the real world, the diffusion processes depend not only on the influences from the past, but also the current (time-evolving) states of the communities, e.g., people's awareness of the disease and people's current interests. In this paper, we propose a novel Hawkes process model that is able to capture the underlying dynamics of community states behind the diffusion processes and predict the occurrences of events based on the dynamics. Specifically, we model the latent dynamic function that encodes these hidden dynamics by a mixture of neural networks. Then we design the triggering kernel using the latent dynamic function and its integral. The proposed method, termed DHP (Dynamic Hawkes Processes), offers a flexible way to learn complex representations of the time-evolving communities' states, while at the same time it allows to computing the exact likelihood, which makes parameter learning tractable. Extensive experiments on four real-world event datasets show that DHP outperforms five widely adopted methods for event prediction.

Tomoharu Iwata

Topic models have been successfully used for analyzing text documents. However, with existing topic models, many documents are required for training. In this paper, we propose a neural network-based few-shot learning method that can learn a topic model from just a few documents. The neural networks in our model take a small number of documents as inputs, and output topic model priors. The proposed method trains the neural networks such that the expected test likelihood is improved when topic model parameters are estimated by maximizing the posterior probability using the priors based on the EM algorithm. Since each step in the EM algorithm is differentiable, the proposed method can backpropagate the loss through the EM algorithm to train the neural networks. The expected test likelihood is maximized by a stochastic gradient descent method using a set of multiple text corpora with an episodic training framework. In our experiments, we demonstrate that the proposed method achieves better perplexity than existing methods using three real-world text document sets.

Tomoharu Iwata

For better clustering performance, appropriate representations are critical. Although many neural network-based metric learning methods have been proposed, they do not directly train neural networks to improve clustering performance. We propose a meta-learning method that train neural networks for obtaining representations such that clustering performance improves when the representations are clustered by the variational Bayesian (VB) inference with an infinite Gaussian mixture model. The proposed method can cluster unseen unlabeled data using knowledge meta-learned with labeled data that are different from the unlabeled data. For the objective function, we propose a continuous approximation of the adjusted Rand index (ARI), by which we can evaluate the clustering performance from soft clustering assignments. Since the approximated ARI and the VB inference procedure are differentiable, we can backpropagate the objective function through the VB inference procedure to train the neural networks. With experiments using text and image data sets, we demonstrate that our proposed method has a higher adjusted Rand index than existing methods do.

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 network-based meta-learning method for supervised anomaly detection. The proposed method improves the anomaly detection performance on unseen tasks, which contains a few labeled normal and anomalous instances, by meta-training with various datasets. With a meta-learning framework, quick adaptation to each task and its effective backpropagation are important since the model is trained by the adaptation for each epoch. Our model enables them by formulating adaptation as a generalized eigenvalue problem with one-class classification; its global optimum solution is obtained, and the solver is differentiable. We experimentally demonstrate that the proposed method achieves better performance than existing anomaly detection and few-shot learning methods on various datasets.

Tomoharu Iwata, Yoshinobu Kawahara

Koopman spectral analysis has attracted attention for nonlinear dynamical systems since we can analyze nonlinear dynamics with a linear regime by embedding data into a Koopman space by a nonlinear function. For the analysis, we need to find appropriate embedding functions. Although several neural network-based methods have been proposed for learning embedding functions, existing methods require long time-series for training neural networks. This limitation prohibits performing Koopman spectral analysis in applications where only short time-series are available. In this paper, we propose a meta-learning method for estimating embedding functions from unseen short time-series by exploiting knowledge learned from related but different time-series. With the proposed method, a representation of a given short time-series is obtained by a bidirectional LSTM for extracting its properties. The embedding function of the short time-series is modeled by a neural network that depends on the time-series representation. By sharing the LSTM and neural networks across multiple time-series, we can learn common knowledge from different time-series while modeling time-series-specific embedding functions with the time-series representation. Our model is trained such that the expected test prediction error is minimized with the episodic training framework. We experimentally demonstrate that the proposed method achieves better performance in terms of eigenvalue estimation and future prediction than existing methods.

Masanori Yamada, Sekitoshi Kanai, Tomoharu Iwata et al.

Adversarial training is actively studied for learning robust models against adversarial examples. A recent study finds that adversarially trained models degenerate generalization performance on adversarial examples when their weight loss landscape, which is loss changes with respect to weights, is sharp. Unfortunately, it has been experimentally shown that adversarial training sharpens the weight loss landscape, but this phenomenon has not been theoretically clarified. Therefore, we theoretically analyze this phenomenon in this paper. As a first step, this paper proves that adversarial training with the L2 norm constraints sharpens the weight loss landscape in the linear logistic regression model. Our analysis reveals that the sharpness of the weight loss landscape is caused by the noise aligned in the direction of increasing the loss, which is used in adversarial training. We theoretically and experimentally confirm that the weight loss landscape becomes sharper as the magnitude of the noise of adversarial training increases in the linear logistic regression model. Moreover, we experimentally confirm the same phenomena in ResNet18 with softmax as a more general case.

Tomoharu Iwata, Yoshinobu Kawahara

Koopman spectral analysis has attracted attention for understanding nonlinear dynamical systems by which we can analyze nonlinear dynamics with a linear regime by lifting observations using a nonlinear function. For analysis, we need to find an appropriate lift function. Although several methods have been proposed for estimating a lift function based on neural networks, the existing methods train neural networks without spectral analysis. In this paper, we propose neural dynamic mode decomposition, in which neural networks are trained such that the forecast error is minimized when the dynamics is modeled based on spectral decomposition in the lifted space. With our proposed method, the forecast error is backpropagated through the neural networks and the spectral decomposition, enabling end-to-end learning of Koopman spectral analysis. When information is available on the frequencies or the growth rates of the dynamics, the proposed method can exploit it as regularizers for training. We also propose an extension of our approach when observations are influenced by exogenous control time-series. Our experiments demonstrate the effectiveness of our proposed method in terms of eigenvalue estimation and forecast performance.

Takashi Wada, Tomoharu Iwata, Yuji Matsumoto et al.

We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously translates and reconstructs an input sentence. Through sharing model parameters among different languages, our model jointly trains the word embeddings in a common cross-lingual space. We also propose to combine word and subword embeddings to make use of orthographic similarities across different languages. We base our experiments on real-world data from endangered languages, namely Yongning Na, Shipibo-Konibo, and Griko. Our experiments on bilingual lexicon induction and word alignment tasks show that our model outperforms existing methods by a large margin for most language pairs. These results demonstrate that, contrary to common belief, an encoder-decoder translation model is beneficial for learning cross-lingual representations even in extremely low-resource conditions. Furthermore, our model also works well on high-resource conditions, achieving state-of-the-art performance on a German-English word-alignment task.

Tomoharu Iwata

Meta-learning is an important approach to improve machine learning performance with a limited number of observations for target tasks. However, when observations are unbalancedly obtained, it is difficult to improve the performance even with meta-learning methods. In this paper, we propose an active learning method for meta-learning on node response prediction tasks in attributed graphs, where nodes to observe are selected to improve performance with as few observed nodes as possible. With the proposed method, we use models based on graph convolutional neural networks for both predicting node responses and selecting nodes, by which we can predict responses and select nodes even for graphs with unseen response variables. The response prediction model is trained by minimizing the expected test error. The node selection model is trained by maximizing the expected error reduction with reinforcement learning. We demonstrate the effectiveness of the proposed method with 11 types of road congestion prediction tasks.

Tomoharu Iwata, Yusuke Tanaka

We propose a few-shot learning method for spatial regression. Although Gaussian processes (GPs) have been successfully used for spatial regression, they require many observations in the target task to achieve a high predictive performance. Our model is trained using spatial datasets on various attributes in various regions, and predicts values on unseen attributes in unseen regions given a few observed data. With our model, a task representation is inferred from given small data using a neural network. Then, spatial values are predicted by neural networks with a GP framework, in which task-specific properties are controlled by the task representations. The GP framework allows us to analytically obtain predictions that are adapted to small data. By using the adapted predictions in the objective function, we can train our model efficiently and effectively so that the test predictive performance improves when adapted to newly given small data. In our experiments, we demonstrate that the proposed method achieves better predictive performance than existing meta-learning methods using spatial datasets.

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 target task might be unavailable, which leads to performance degradation. In this paper, we propose a few-shot learning method that forecasts a future value of a time-series in a target task given a few time-series in the target task. Our model is trained using time-series data in multiple training tasks that are different from target tasks. Our model uses a few time-series to build a forecasting function based on a recurrent neural network with an attention mechanism. With the attention mechanism, we can retrieve useful patterns in a small number of time-series for the current situation. Our model is trained by minimizing an expected test error of forecasting next timestep values. We demonstrate the effectiveness of the proposed method using 90 time-series datasets.

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.

Yasunori Akagi, Yusuke Tanaka, Tomoharu Iwata et al.

Optimal Transport (OT) is being widely used in various fields such as machine learning and computer vision, as it is a powerful tool for measuring the similarity between probability distributions and histograms. In previous studies, OT has been defined as the minimum cost to transport probability mass from one probability distribution to another. In this study, we propose a new framework in which OT is considered as a maximum a posteriori (MAP) solution of a probabilistic generative model. With the proposed framework, we show that OT with entropic regularization is equivalent to maximizing a posterior probability of a probabilistic model called Collective Graphical Model (CGM), which describes aggregated statistics of multiple samples generated from a graphical model. Interpreting OT as a MAP solution of a CGM has the following two advantages: (i) We can calculate the discrepancy between noisy histograms by modeling noise distributions. Since various distributions can be used for noise modeling, it is possible to select the noise distribution flexibly to suit the situation. (ii) We can construct a new method for interpolation between histograms, which is an important application of OT. The proposed method allows for intuitive modeling based on the probabilistic interpretations, and a simple and efficient estimation algorithm is available. Experiments using synthetic and real-world spatio-temporal population datasets show the effectiveness of the proposed interpolation method.

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.

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 anomaly detection methods it is usually assumed that instances are independent and identically distributed, in many real-world applications, instances are often explicitly connected with each other, resulting in so-called attributed graphs. The proposed method embeds nodes (instances) on the attributed graph in the latent space by taking into account their attributes as well as the graph structure based on graph convolutional networks (GCNs). To learn node embeddings specialized for anomaly detection, in which there is a class imbalance due to the rarity of anomalies, the parameters of a GCN are trained to minimize the volume of a hypersphere that encloses the node embeddings of normal instances while embedding anomalous ones outside the hypersphere. This enables us to detect anomalies by simply calculating the distances between the node embeddings and hypersphere center. The proposed method can effectively propagate label information on a small amount of nodes to unlabeled ones by taking into account the node's attributes, graph structure, and class imbalance. In experiments with five real-world attributed graph datasets, we demonstrate that the proposed method achieves better performance than various existing anomaly detection methods.