Hayate Kojima
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hayate Kojima has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hiroshi Higashi
The University of Osaka
1 shared publication - Junya Hara
Graduate School of Engineering, The University of Osaka, Osaka, Japan
1 shared publication - Keigo Takanami
Graduate School of Engineering, Tokyo University of Agriculture and Technology, Tokyo, Japan
1 shared publication - Seishi Takamura
Graduate School of Computer and Information Sciences, Hosei University, Tokyo, Japan
1 shared publication - Yuichi Tanaka
Graduate School of Engineering, The University of Osaka, Osaka, Japan
1 shared publication - Yukihiro Bandoh
Shimonoseki City University, Yamaguchi, Japan
1 shared publication
Latest Publications
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 12, 544-555
Algorithm Unrolling-Based Denoising of Multimodal Graph Signals
We propose a denoising method for multimodal graph signals by an alternating minimization scheme that sequentially solves signal restoration and graph learning problems. Many complex-structured data, i.e., those on sensor networks, can capture multiple modalities at each measurement point, referred to as modalities. They are also assumed to have an underlying structure or correlations in the modality domain as well as in space. Such multimodal data are regarded as graph signals on a twofold graph and they are often corrupted by noise. Furthermore, their spatial/modality relationships are not always given a priori: We need to estimate twofold graphs during a denoising algorithm. In this paper, we consider a signal denoising method on twofold graphs, where graphs are learned simultaneously. Specifically, the graph learning subproblems are solved using the primal-dual splitting (PDS) algorithm, while the signal update has a closed-form solution. Parameters in this iterative algorithm are learned from training data by unrolling the iteration with deep algorithm unrolling. Experimental results on synthetic and real-world data demonstrate that the proposed method outperforms existing model- and deep learning-based graph signal denoising methods.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 12, 544-555
Algorithm Unrolling-Based Denoising of Multimodal Graph Signals
We propose a denoising method for multimodal graph signals by an alternating minimization scheme that sequentially solves signal restoration and graph learning problems. Many complex-structured data, i.e., those on sensor networks, can capture multiple modalities at each measurement point, referred to as modalities. They are also assumed to have an underlying structure or correlations in the modality domain as well as in space. Such multimodal data are regarded as graph signals on a twofold graph and they are often corrupted by noise. Furthermore, their spatial/modality relationships are not always given a priori: We need to estimate twofold graphs during a denoising algorithm. In this paper, we consider a signal denoising method on twofold graphs, where graphs are learned simultaneously. Specifically, the graph learning subproblems are solved using the primal-dual splitting (PDS) algorithm, while the signal update has a closed-form solution. Parameters in this iterative algorithm are learned from training data by unrolling the iteration with deep algorithm unrolling. Experimental results on synthetic and real-world data demonstrate that the proposed method outperforms existing model- and deep learning-based graph signal denoising methods.