Hideaki Ishibashi

Hideaki Ishibashi

Auto-generated profile, based on publicly available information

Hideaki Ishibashi

Kyushu Institute of Technology

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2022 in Neurocomputing
Verified
Journal Article
Closed access
HIHideaki Ishibashi
Hideaki Ishibashi
KHKazushi Higa
Kazushi Higa
TFTetsuo Furukawa
Tetsuo Furukawa

26 July 2023 in Neural Networks
Verified
Journal Article
Open access
KSKotaro Sakamoto
Kotaro Sakamoto
HIHideaki Ishibashi
Hideaki Ishibashi
RSRei Sato
Rei Sato
SSShinichi Shirakawa
Shinichi Shirakawa
YAYouhei Akimoto
Youhei Akimoto
HHHideitsu Hino
Hideitsu Hino
Neural architecture search (NAS) is a framework for automating the design process of a neural network structure. While the recent one-shot approaches have reduced the search cost, there still exists an inherent trade-off between cost and performance. It is important to appropriately stop the search and further reduce the high cost of NAS. Meanwhile, the differentiable architecture search (DARTS), a typical one-shot approach, is known to suffer from overfitting. Heuristic early-stopping strategies have been proposed to overcome such performance degradation. In this paper, we propose a more versatile and principled early-stopping criterion on the basis of the evaluation of a gap between expectation values of generalisation errors of the previous and current search steps with respect to the architecture parameters. The stopping threshold is automatically determined at each search epoch without cost. In numerical experiments, we demonstrate the effectiveness of the proposed method. We stop the one-shot NAS algorithms and evaluate the acquired architectures on the benchmark datasets: NAS-Bench-201 and NATS-Bench. Our algorithm is shown to reduce the cost of the search process while maintaining a high performance.

15 April 2022 in Neural Computation
Verified
Journal Article
Closed access
PDF file
HIHideaki Ishibashi
Hideaki Ishibashi
SAShotaro Akaho
Shotaro Akaho
This letter proposes an extension of principal component analysis for gaussian process (GP) posteriors, denoted by GP-PCA. Since GP-PCA estimates a low-dimensional space of GP posteriors, it can be used for metalearning, a framework for improving the performance of target tasks by estimating a structure of a set of tasks. The issue is how to define a structure of a set of GPs with an infinite-dimensional parameter, such as coordinate system and a divergence. In this study, we reduce the infiniteness of GP to the finite-dimensional case under the information geometrical framework by considering a space of GP posteriors that have the same prior. In addition, we propose an approximation method of GP-PCA based on variational inference and demonstrate the effectiveness of GP-PCA as meta-learning through experiments.

1 January 2022 in Decision Support Systems
Verified
Journal Article
Closed access
RWRyuji Watanabe
Ryuji Watanabe
HIHideaki Ishibashi
Hideaki Ishibashi
TFTetsuo Furukawa
Tetsuo Furukawa

9 April 2021 in arXiv
Verified
Preprint
Open access
PDF file
HIHideaki Ishibashi
Hideaki Ishibashi
HHHideitsu Hino
Hideitsu Hino
Active learning is a framework for supervised learning to improve the predictive performance by adaptively annotating a small number of samples. To realize efficient active learning, both an acquisition function that determines the next datum and a stopping criterion that determines when to stop learning should be considered. In this study, we propose a stopping criterion based on error stability, which guarantees that the change in generalization error upon adding a new sample is bounded by the annotation cost and can be applied to any Bayesian active learning. We demonstrate that the proposed criterion stops active learning at the appropriate timing for various learning models and real datasets.

23 September 2025
Verified
Book Chapter
Closed access
PDF file
HIHideaki Ishibashi
Hideaki Ishibashi
KMKota Matsui
Kota Matsui
KKKentaro Kutsukake
Kentaro Kutsukake
HHHideitsu Hino
Hideitsu Hino