Ryuichiro Hataya

Ryuichiro Hataya, Makoto Yamada

The essential difficulty of gradient-based bilevel optimization using implicit differentiation is to estimate the inverse Hessian vector product with respect to neural network parameters. This paper proposes to tackle this problem by the Nystrom method and the Woodbury matrix identity, exploiting the low-rankness of the Hessian. Compared to existing methods using iterative approximation, such as conjugate gradient and the Neumann series approximation, the proposed method avoids numerical instability and can be efficiently computed in matrix operations without iterations. As a result, the proposed method works stably in various tasks and is faster than iterative approximations. Throughout experiments including large-scale hyperparameter optimization and meta learning, we demonstrate that the Nystrom method consistently achieves comparable or even superior performance to other approaches. The source code is available from https://github.com/moskomule/hypergrad.

Ryuichiro Hataya, Han Bao, Hiromi Arai

Recently proposed large-scale text-to-image generative models such as DALL$\cdot$E 2, Midjourney, and StableDiffusion can generate high-quality and realistic images from users' prompts. Not limited to the research community, ordinary Internet users enjoy these generative models, and consequently, a tremendous amount of generated images have been shared on the Internet. Meanwhile, today's success of deep learning in the computer vision field owes a lot to images collected from the Internet. These trends lead us to a research question: "\textbf{will such generated images impact the quality of future datasets and the performance of computer vision models positively or negatively?}" This paper empirically answers this question by simulating contamination. Namely, we generate ImageNet-scale and COCO-scale datasets using a state-of-the-art generative model and evaluate models trained with "contaminated" datasets on various tasks, including image classification and image generation. Throughout experiments, we conclude that generated images negatively affect downstream performance, while the significance depends on tasks and the amount of generated images. The generated datasets and the codes for experiments will be publicly released for future research. Generated datasets and source codes are available from \url{https://github.com/moskomule/dataset-contamination}.

Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui

Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon. In this paper, we introduce complexity minimization, a novel meta-representation learning framework designed to enable theoretical analysis of this scaling behavior, which learns representations by evaluating the downstream model complexity best suited to each domain and minimizing the worst-case such complexity across source domains. Our end-to-end theoretical analysis, spanning pre-training through downstream regression, shows that this framework provably captures this scaling behavior; in particular, we show that the error rate of few-shot adaptation improves as the amount of meta-training data grows. Empirically, we demonstrate that incorporating complexity regularization into existing meta-learning methods consistently improves downstream sample efficiency.

Kazuma Kobayashi, Lin Gu, Ryuichiro Hataya et al.

The amount of medical images stored in hospitals is increasing faster than ever; however, utilizing the accumulated medical images has been limited. This is because existing content-based medical image retrieval (CBMIR) systems usually require example images to construct query vectors; nevertheless, example images cannot always be prepared. Besides, there can be images with rare characteristics that make it difficult to find similar example images, which we call isolated samples. Here, we introduce a novel sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without example images. The key idea lies in feature decomposition of medical images, whereby the entire feature of a medical image can be decomposed into and reconstructed from normal and abnormal features. By extending this idea, our SBMIR system provides an easy-to-use two-step graphical user interface: users first select a template image to specify a normal feature and then draw a semantic sketch of the disease on the template image to represent an abnormal feature. Subsequently, it integrates the two kinds of input to construct a query vector and retrieves reference images with the closest reference vectors. Using two datasets, ten healthcare professionals with various clinical backgrounds participated in the user test for evaluation. As a result, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for isolated samples. Our SBMIR system achieves flexible medical image retrieval on demand, thereby expanding the utility of medical image databases.

Leonardo Placidi, Ryuichiro Hataya, Toshio Mori et al.

We introduce the first large-scale dataset, MNISQ, for both the Quantum and the Classical Machine Learning community during the Noisy Intermediate-Scale Quantum era. MNISQ consists of 4,950,000 data points organized in 9 subdatasets. Building our dataset from the quantum encoding of classical information (e.g., MNIST dataset), we deliver a dataset in a dual form: in quantum form, as circuits, and in classical form, as quantum circuit descriptions (quantum programming language, QASM). In fact, also the Machine Learning research related to quantum computers undertakes a dual challenge: enhancing machine learning exploiting the power of quantum computers, while also leveraging state-of-the-art classical machine learning methodologies to help the advancement of quantum computing. Therefore, we perform circuit classification on our dataset, tackling the task with both quantum and classical models. In the quantum endeavor, we test our circuit dataset with Quantum Kernel methods, and we show excellent results up to $97\%$ accuracy. In the classical world, the underlying quantum mechanical structures within the quantum circuit data are not trivial. Nevertheless, we test our dataset on three classical models: Structured State Space sequence model (S4), Transformer and LSTM. In particular, the S4 model applied on the tokenized QASM sequences reaches an impressive $77\%$ accuracy. These findings illustrate that quantum circuit-related datasets are likely to be quantum advantageous, but also that state-of-the-art machine learning methodologies can competently classify and recognize quantum circuits. We finally entrust the quantum and classical machine learning community the fundamental challenge to build more quantum-classical datasets like ours and to build future benchmarks from our experiments. The dataset is accessible on GitHub and its circuits are easily run in qulacs or qiskit.

Ryuichiro Hataya, Yuka Hashimoto

We propose a new generalization of neural network parameter spaces with noncommutative $C^*$-algebra, which possesses a rich noncommutative structure of products. We show that this noncommutative structure induces powerful effects in learning neural networks. Our framework has a wide range of applications, such as learning multiple related neural networks simultaneously with interactions and learning equivariant features with respect to group actions. Numerical experiments illustrate the validity of our framework and its potential power.

Hiroki Naganuma, Ryuichiro Hataya, Kotaro Yoshida et al.

In the field of computer vision, fine-tuning pre-trained models has become a prevalent strategy for out-of-distribution (OOD) generalization tasks. Different from most prior work that has focused on advancing learning algorithms, we systematically examined how pre-trained model size, pre-training dataset size, and training strategies impact generalization and confidence calibration on downstream tasks. We evaluated 100 models across diverse pre-trained model sizes, five pre-training datasets, and five data augmentations through extensive experiments on four distribution shift datasets totaling over 120,000 GPU hours. Our results demonstrate the significant impact of pre-trained model selection, with optimal choices substantially improving OOD accuracy over algorithm improvement alone. Additionally, we find that larger models and bigger pre-training datasets not only enhance OOD performance but also improve calibration, helping to mitigate overconfidence, contrary to some prior studies that found modern deep networks to calibrate worse than classical shallow models. Our work underscores the overlooked importance of pre-trained model selection for out-of-distribution generalization and calibration.

Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate that larger pre-trained models can significantly reduce the sample complexity of downstream learning. However, existing theoretical investigations of pre-trained models lack the capability to explain this phenomenon. In this paper, we provide a theoretical investigation by introducing a novel framework, caulking, inspired by parameter-efficient fine-tuning (PEFT) methods such as adapter-based fine-tuning, low-rank adaptation, and partial fine-tuning. Our analysis establishes that improved pre-trained models provably decrease the sample complexity of downstream tasks, thereby offering theoretical justification for the empirically observed scaling laws relating pre-trained model size to downstream performance, a relationship not covered by existing results.

Han Bao, Ryuichiro Hataya, Ryo Karakida

The self-attention mechanism prevails in modern machine learning. It has an interesting functionality of adaptively selecting tokens from an input sequence by modulating the degree of attention localization, which many researchers speculate is the basis of the powerful model performance but complicates the underlying mechanism of the learning dynamics. In recent years, mainly two arguments have connected attention localization to the model performances. One is the rank collapse, where the embedded tokens by a self-attention block become very similar across different tokens, leading to a less expressive network. The other is the entropy collapse, where the attention probability approaches non-uniform and entails low entropy, making the learning dynamics more likely to be trapped in plateaus. These two failure modes may apparently contradict each other because the rank and entropy collapses are relevant to uniform and non-uniform attention, respectively. To this end, we characterize the notion of attention localization by the eigenspectrum of query-key parameter matrices and reveal that a small eigenspectrum variance leads attention to be localized. Interestingly, the small eigenspectrum variance prevents both rank and entropy collapse, leading to better model expressivity and trainability.

Ryuichiro Hataya, Yoshinobu Kawahara

Gradient-based hyperparameter optimization methods update hyperparameters using hypergradients, gradients of a meta criterion with respect to hyperparameters. Previous research used two distinct update strategies: optimizing hyperparameters using global hypergradients obtained after completing model training or local hypergradients derived after every few model updates. While global hypergradients offer reliability, their computational cost is significant; conversely, local hypergradients provide speed but are often suboptimal. In this paper, we propose *glocal* hypergradient estimation, blending "global" quality with "local" efficiency. To this end, we use the Koopman operator theory to linearize the dynamics of hypergradients so that the global hypergradients can be efficiently approximated only by using a trajectory of local hypergradients. Consequently, we can optimize hyperparameters greedily using estimated global hypergradients, achieving both reliability and efficiency simultaneously. Through numerical experiments of hyperparameter optimization, including optimization of optimizers, we demonstrate the effectiveness of the glocal hypergradient estimation.

Yuka Hashimoto, Ryuichiro Hataya

This paper introduces quantum circuit $C^*$-algebra net, which provides a connection between $C^*$-algebra nets proposed in classical machine learning and quantum circuits. Using $C^*$-algebra, a generalization of the space of complex numbers, we can represent quantum gates as weight parameters of a neural network. By introducing additional parameters, we can induce interaction among multiple circuits constructed by quantum gates. This interaction enables the circuits to share information among them, which contributes to improved generalization performance in machine learning tasks. As an application, we propose to use the quantum circuit $C^*$-algebra net to encode classical data into quantum states, which enables us to integrate classical data into quantum algorithms. Numerical results demonstrate that the interaction among circuits improves performance significantly in image classification, and encoded data by the quantum circuit $C^*$-algebra net are useful for downstream quantum machine learning tasks.

Kazuma Kobayashi, Ryuichiro Hataya, Yusuke Kurose et al.

In medical imaging, the characteristics purely derived from a disease should reflect the extent to which abnormal findings deviate from the normal features. Indeed, physicians often need corresponding images without abnormal findings of interest or, conversely, images that contain similar abnormal findings regardless of normal anatomical context. This is called comparative diagnostic reading of medical images, which is essential for a correct diagnosis. To support comparative diagnostic reading, content-based image retrieval (CBIR), which can selectively utilize normal and abnormal features in medical images as two separable semantic components, will be useful. Therefore, we propose a neural network architecture to decompose the semantic components of medical images into two latent codes: normal anatomy code and abnormal anatomy code. The normal anatomy code represents normal anatomies that should have existed if the sample is healthy, whereas the abnormal anatomy code attributes to abnormal changes that reflect deviation from the normal baseline. These latent codes are discretized through vector quantization to enable binary hashing, which can reduce the computational burden at the time of similarity search. By calculating the similarity based on either normal or abnormal anatomy codes or the combination of the two codes, our algorithm can retrieve images according to the selected semantic component from a dataset consisting of brain magnetic resonance images of gliomas. Our CBIR system qualitatively and quantitatively achieves remarkable results.

Ryuichiro Hataya, Hideki Nakayama, Kazuki Yoshizoe

It is common practice for chemists to search chemical databases based on substructures of compounds for finding molecules with desired properties. The purpose of de novo molecular generation is to generate instead of search. Existing machine learning based molecular design methods have no or limited ability in generating novel molecules that preserves a target substructure. Our Graph Energy-based Model, or GEM, can fix substructures and generate the rest. The experimental results show that the GEMs trained from chemistry datasets successfully generate novel molecules while preserving the target substructures. This method would provide a new way of incorporating the domain knowledge of chemists in molecular design.

Kazuma Kobayashi, Ryuichiro Hataya, Yusuke Kurose et al.

Medical images can be decomposed into normal and abnormal features, which is considered as the compositionality. Based on this idea, we propose an encoder-decoder network to decompose a medical image into two discrete latent codes: a normal anatomy code and an abnormal anatomy code. Using these latent codes, we demonstrate a similarity retrieval by focusing on either normal or abnormal features of medical images.

Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe et al.

Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. In this paper, we propose to optimize image recognition models and data augmentation policies simultaneously to improve the performance using gradient descent. Unlike prior methods, our approach avoids using proxy tasks or reducing search space, and can directly improve the validation performance. Our method achieves efficient and scalable training by approximating the gradient of policies by implicit gradient with Neumann series approximation. We demonstrate that our approach can improve the performance of various image classification tasks, including ImageNet classification and fine-grained recognition, without using dataset-specific hyperparameter tuning.

Kazuma Kobayashi, Ryuichiro Hataya, Yusuke Kurose et al.

In real-world clinical practice, overlooking unanticipated findings can result in serious consequences. However, supervised learning, which is the foundation for the current success of deep learning, only encourages models to identify abnormalities that are defined in datasets in advance. Therefore, abnormality detection must be implemented in medical images that are not limited to a specific disease category. In this study, we demonstrate an unsupervised learning framework for pixel-wise abnormality detection in brain magnetic resonance imaging captured from a patient population with metastatic brain tumor. Our concept is as follows: If an image reconstruction network can faithfully reproduce the global features of normal anatomy, then the abnormal lesions in unseen images can be identified based on the local difference from those reconstructed as normal by a discriminative network. Both networks are trained on a dataset comprising only normal images without labels. In addition, we devise a metric to evaluate the anatomical fidelity of the reconstructed images and confirm that the overall detection performance is improved when the image reconstruction network achieves a higher score. For evaluation, clinically significant abnormalities are comprehensively segmented. The results show that the area under the receiver operating characteristics curve values for metastatic brain tumors, extracranial metastatic tumors, postoperative cavities, and structural changes are 0.78, 0.61, 0.91, and 0.60, respectively.

Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe et al.

Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms outperform hand-made strategies. Such methods employ black-box search algorithms over image transformations with continuous or discrete parameters and require a long time to obtain better strategies. In this paper, we propose a differentiable policy search pipeline for data augmentation, which is much faster than previous methods. We introduce approximate gradients for several transformation operations with discrete parameters as well as the differentiable mechanism for selecting operations. As the objective of training, we minimize the distance between the distributions of augmented data and the original data, which can be differentiated. We show that our method, Faster AutoAugment, achieves significantly faster searching than prior work without a performance drop.

Leonardo Rundo, Changhee Han, Yudai Nagano et al.

Prostate cancer is the most common malignant tumors in men but prostate Magnetic Resonance Imaging (MRI) analysis remains challenging. Besides whole prostate gland segmentation, the capability to differentiate between the blurry boundary of the Central Gland (CG) and Peripheral Zone (PZ) can lead to differential diagnosis, since tumor's frequency and severity differ in these regions. To tackle the prostate zonal segmentation task, we propose a novel Convolutional Neural Network (CNN), called USE-Net, which incorporates Squeeze-and-Excitation (SE) blocks into U-Net. Especially, the SE blocks are added after every Encoder (Enc USE-Net) or Encoder-Decoder block (Enc-Dec USE-Net). This study evaluates the generalization ability of CNN-based architectures on three T2-weighted MRI datasets, each one consisting of a different number of patients and heterogeneous image characteristics, collected by different institutions. The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training/testing combinations. USE-Net is compared against three state-of-the-art CNN-based architectures (i.e., U-Net, pix2pix, and Mixed-Scale Dense Network), along with a semi-automatic continuous max-flow model. The results show that training on the union of the datasets generally outperforms training on each dataset separately, allowing for both intra-/cross-dataset generalization. Enc USE-Net shows good overall generalization under any training condition, while Enc-Dec USE-Net remarkably outperforms the other methods when trained on all datasets. These findings reveal that the SE blocks' adaptive feature recalibration provides excellent cross-dataset generalization when testing is performed on samples of the datasets used during training.

Leonardo Rundo, Changhee Han, Jin Zhang et al.

Prostate cancer is the most common cancer among US men. However, prostate imaging is still challenging despite the advances in multi-parametric Magnetic Resonance Imaging (MRI), which provides both morphologic and functional information pertaining to the pathological regions. Along with whole prostate gland segmentation, distinguishing between the Central Gland (CG) and Peripheral Zone (PZ) can guide towards differential diagnosis, since the frequency and severity of tumors differ in these regions; however, their boundary is often weak and fuzzy. This work presents a preliminary study on Deep Learning to automatically delineate the CG and PZ, aiming at evaluating the generalization ability of Convolutional Neural Networks (CNNs) on two multi-centric MRI prostate datasets. Especially, we compared three CNN-based architectures: SegNet, U-Net, and pix2pix. In such a context, the segmentation performances achieved with/without pre-training were compared in 4-fold cross-validation. In general, U-Net outperforms the other methods, especially when training and testing are performed on multiple datasets.