Author name cluster

Ikuro Sato

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

9 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Masked Gated Linear Unit

Yukito Tajima
Nakamasa Inoue
Yusuke Sekikawa
Ikuro Sato
Rio Yokota

Gated Linear Units (GLUs) have become essential components in the feed-forward networks of state-of-the-art Large Language Models (LLMs). However, they require twice as many memory reads compared to feed-forward layers without gating, due to the use of separate weight matrices for the gate and value streams. To address this bottleneck, we introduce Masked Gated Linear Units (MGLUs), a novel family of GLUs with an efficient kernel implementation. The core contribution of MGLUs include: (1) the Mixture of Element-wise Gating (MoEG) architecture that learns multiple binary masks, each determining gate or value assignments at the element level on a single shared weight matrix resulting in reduced memory transfer, and (2) FlashMGLU, a hardware-friendly kernel that yields up to a 19. 7$\times$ inference-time speed-up over a na\"ive PyTorch MGLU and is 47\% more memory-efficient and 34\% faster than standard GLUs despite added architectural complexity on an RTX5090 GPU. In LLM experiments, the Swish-activated variant SwiMGLU preserves its memory advantages while matching—or even surpassing—the downstream accuracy of the SwiGLU baseline.

PDF Details

AAAI Conference 2025 Conference Paper

Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks

Ryo Moriai
Nakamasa Inoue
Masayuki Tanaka
Rei Kawakami
Satoshi Ikehata
Ikuro Sato

Modern Hopfield networks (MHNs) have recently gained significant attention in the field of artificial intelligence because they can store and retrieve a large set of patterns with an exponentially large memory capacity. A MHN is generally a dynamical system defined with Lagrangians of memory and feature neurons,where memories associated with in-distribution (ID) samples are represented by attractors in the feature space. One major problem in existing MHNs lies in managing out-of-distribution (OOD) samples because it was originally assumed that all samples are ID samples. To address this, we propose the rectified Lagrangian (RegLag), a new Lagrangian for memory neurons that explicitly incorporates an attractor for OOD samples in the dynamical system of MHNs. RecLag creates a trivial point attractor for any interaction matrix, enabling OOD detection by identifying samples that fall into this attractor as OOD. The interaction matrix is optimized so that the probability densities can be estimated to identify ID/OOD. We demonstrate the effectiveness of RecLag-based MHNs compared to energy-based OOD detection methods, including those using state-of-the-art Hopfield energies, across nine image datasets.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Efficient Target Propagation by Deriving Analytical Solution

Yanhao Bao
Tatsukichi Shibuya
Ikuro Sato
Rei Kawakami
Nakamasa Inoue

Exploring biologically plausible algorithms as alternatives to error backpropagation (BP) is a challenging research topic in artificial intelligence. It also provides insights into the brain's learning methods. Recently, when combined with well-designed feedback loss functions such as Local Difference Reconstruction Loss (LDRL) and through hierarchical training of feedback pathway synaptic weights, Target Propagation (TP) has achieved performance comparable to BP in image classification tasks. However, with an increase in the number of network layers, the tuning and training cost of feedback weights escalates. Drawing inspiration from the work of Ernoult et al., we propose a training method that seeks the optimal solution for feedback weights. This method enhances the efficiency of feedback training by analytically minimizing feedback loss, allowing the feedback layer to skip certain local training iterations. More specifically, we introduce the Jacobian matching loss (JML) for feedback training. We also proactively implement layers designed to derive analytical solutions that minimize JML. Through experiments, we have validated the effectiveness of this approach. Using the CIFAR-10 dataset, our method showcases accuracy levels comparable to state-of-the-art TP methods. Furthermore, we have explored its effectiveness in more intricate network architectures.

PDF Details DOI

TMLR Journal 2023 Journal Article

Empirical Study on Optimizer Selection for Out-of-Distribution Generalization

Hiroki Naganuma
Kartik Ahuja
Shiro Takagi
Tetsuya Motokawa
Rio Yokota
Kohta Ishikawa
Ikuro Sato
Ioannis Mitliagkas

Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution. While much promising work has been accomplished to address this fragility, a systematic study of the role of optimizers and their out-of-distribution generalization performance has not been undertaken. In this study, we examine the performance of popular first-order optimizers for different classes of distributional shift under empirical risk minimization and invariant risk minimization. We address this question for image and text classification using DomainBed, WILDS, and Backgrounds Challenge as testbeds for studying different types of shifts---namely correlation and diversity shift. We search over a wide range of hyperparameters and examine classification accuracy (in-distribution and out-of-distribution) for over 20,000 models. We arrive at the following findings, which we expect to be helpful for practitioners: i) adaptive optimizers (e.g., Adam) perform worse than non-adaptive optimizers (e.g., SGD, momentum SGD) on out-of-distribution performance. In particular, even though there is no significant difference in in-distribution performance, we show a measurable difference in out-of-distribution performance. ii) in-distribution performance and out-of-distribution performance exhibit three types of behavior depending on the dataset---linear returns, increasing returns, and diminishing returns. For example, in the training of natural language data using Adam, fine-tuning the performance of in-distribution performance does not significantly contribute to the out-of-distribution generalization performance.

PDF Details

AAAI Conference 2023 Conference Paper

Fixed-Weight Difference Target Propagation

Tatsukichi Shibuya
Nakamasa Inoue
Rei Kawakami
Ikuro Sato

Target Propagation (TP) is a biologically more plausible algorithm than the error backpropagation (BP) to train deep networks, and improving practicality of TP is an open issue. TP methods require the feedforward and feedback networks to form layer-wise autoencoders for propagating the target values generated at the output layer. However, this causes certain drawbacks; e.g., careful hyperparameter tuning is required to synchronize the feedforward and feedback training, and frequent updates of the feedback path are usually required than that of the feedforward path. Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work? We answer this question by presenting Fixed-Weight Difference Target Propagation (FW-DTP) that keeps the feedback weights constant during training. We confirmed that this simple method, which naturally resolves the abovementioned problems of TP, can still deliver informative target values to hidden layers for a given task; indeed, FW-DTP consistently achieves higher test performance than a baseline, the Difference Target Propagation (DTP), on four classification datasets. We also present a novel propagation architecture that explains the exact form of the feedback function of DTP to analyze FW-DTP. Our code is available at https://github.com/TatsukichiShibuya/Fixed-Weight-Difference-Target-Propagation.

PDF Details DOI

ICML Conference 2022 Conference Paper

Feature Space Particle Inference for Neural Network Ensembles

Shingo Yashima
Teppei Suzuki
Kohta Ishikawa
Ikuro Sato
Rei Kawakami

Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-based inference methods offer a promising approach from a Bayesian perspective. However, the best way to apply these methods to neural networks is still unclear: seeking samples from the weight-space posterior suffers from inefficiency due to the over-parameterization issues, while seeking samples directly from the function-space posterior often leads to serious underfitting. In this study, we propose to optimize particles in the feature space where activations of a specific intermediate layer lie to alleviate the abovementioned difficulties. Our method encourages each member to capture distinct features, which are expected to increase the robustness of the ensemble prediction. Extensive evaluation on real-world datasets exhibits that our model significantly outperforms the gold-standard Deep Ensembles on various metrics, including accuracy, calibration, and robustness.

Details

ICML Conference 2022 Conference Paper

PoF: Post-Training of Feature Extractor for Improving Generalization

Ikuro Sato
Ryota Yamada
Masayuki Tanaka 0001
Nakamasa Inoue
Rei Kawakami

It has been intensively investigated that the local shape, especially flatness, of the loss landscape near a minimum plays an important role for generalization of deep models. We developed a training algorithm called PoF: Post-Training of Feature Extractor that updates the feature extractor part of an already-trained deep model to search a flatter minimum. The characteristics are two-fold: 1) Feature extractor is trained under parameter perturbations in the higher-layer parameter space, based on observations that suggest flattening higher-layer parameter space, and 2) the perturbation range is determined in a data-driven manner aiming to reduce a part of test loss caused by the positive loss curvature. We provide a theoretical analysis that shows the proposed algorithm implicitly reduces the target Hessian components as well as the loss. Experimental results show that PoF improved model performance against baseline methods on both CIFAR-10 and CIFAR-100 datasets for only 10-epoch post-training, and on SVHN dataset for 50-epoch post-training.

Details

AAAI Conference 2020 Conference Paper

Adversarial Transformations for Semi-Supervised Learning

Teppei Suzuki
Ikuro Sato

We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning. RAT is designed to enhance robustness of the output distribution of class prediction for a given data against input perturbation. RAT is an extension of Virtual Adversarial Training (VAT) in such a way that RAT adversraialy transforms data along the underlying data distribution by a rich set of data transformation functions that leave class label invariant, whereas VAT simply produces adversarial additive noises. In addition, we veriﬁed that a technique of gradually increasing of perturbation region further improves the robustness. In experiments, we show that RAT signiﬁcantly improves classiﬁcation performance on CIFAR-10 and SVHN compared to existing regularization methods under standard semi-supervised image classiﬁcation settings.

PDF Details

ICML Conference 2019 Conference Paper

Breaking Inter-Layer Co-Adaptation by Classifier Anonymization

Ikuro Sato
Kohta Ishikawa
Guoqing Liu
Masayuki Tanaka 0001

This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimization. We put forth a mathematical proposition that states the FOCA features form a point-like distribution within the same class in a class-separable fashion under special conditions. Real-data experiments under more general conditions provide supportive evidences.

Details