I am a researcher of Machine Learning at NTT in Tokyo, Japan.

My interests lie in the fields of deep learning, sparse modeling and optimal transport.

Google Scholar, DBLP

E-mail: ystsh521 [at] gmail [dot] com

Selected Papers


Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance

Fast feature/data selection from data matrix with accuracy assurance.

Y. Ida, S. Kanai, Y. Fujiwara, T. Iwata, K. Takeuchi, H. Kashima

International Conference on Machine Learning (ICML), 2020.

[paper] [slide]

Fast Sparse Group Lasso

Fast feature selection for group structured data with accuracy assurance.

Y. Ida, Y. Fujiwara, H. Kashima

Neural Information Processing Systems (NeurIPS), 2019.

[paper] [slide]

Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks

Fast training algorithm for deep neural networks.

Y. Ida, Y. Fujiwara, S. Iwamura

International Joint Conference on Artificial Intelligence (IJCAI), 2017.

[paper] [slide]

Domain-Dependent/Independent Topic Switching Model for Online Reviews with Numerical Ratings

Probabilistic model for texts with various attributes.

Y. Ida, T. Nakamura, T. Matsumoto

ACM International Conference on Information and Knowledge Management (CIKM), 2013.

[paper]

Publication List


International Conference Papers

  1. Y. Ida, S. Kanai, A. Kumagai, T. Iwata, Y. Fujiwara,
    Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations,
    Neural Information Processing Systems (NeurIPS), 2024, to appear.

  2. Y. Fujiwara, A. Kumagai, Y. Ida, M. Nakano, M. Nakatsuji, A. Kimura,
    Efficient Algorithm for K-Multiple-Means,
    Special Interest Group on Management of Data (SIGMOD), 2024, to appear.

  3. S. Kanai, S. Yamaguchi, M. Yamada, H. Takahashi, K. Ohno, Y. Ida,
    One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training,
    International Conference on Machine Learning (ICML), 2023.
    [paper]

  4. Y. Ida, S. Kanai, A. Kumagai,
    Fast Block Coordinate Descent for Non-Convex Group Regularizations,
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
    [paper]

  5. Y. Fujiwara, Y. Ida, A. Kumagai, M. Nakano, A. Kimura, N. Ueda
    Efficient Network Representation Learning via Cluster Similarity,
    International Conference on Database Systems for Advanced Applications (DASFAA), 2023.
    [paper]

  6. Y. Ida, S. Kanai, K. Adachi, A. Kumagai, Y. Fujiwara,
    Fast Regularized Discrete Optimal Transport with Group-sparse Regularizers,
    Association for the Advancement of Artificial Intelligence (AAAI), 2023.
    [preprint] [slide] [poster]

  7. K. Ohno, S. Kanai, Y. Ida,
    Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks,
    Association for the Advancement of Artificial Intelligence (AAAI), 2023.
    [preprint]

  8. Y. Fujiwara, M. Nakano, A.Kumagai, Y. Ida, A. Kimura, N. Ueda,
    Fast Binary Network Hashing via Graph Clustering,
    IEEE BigData, 2022.

  9. A. Kumagai, T. Iwata, Y. Ida, Y. Fujiwara,
    Meta-learning for Feature Selection with Hilbert-Schmidt Independence Criterion,
    Neural Information Processing Systems (NeurIPS), 2022.

  10. D. Chijiwa, S. Yamaguchi, A. Kumagai, Y. Ida,
    Meta-ticket: Finding Optimal Subnetworks for Few-shot Learning within Randomly Initialized Neural Networks,
    Neural Information Processing Systems (NeurIPS), 2022.

  11. Y, Fujiwara, Y. Ida, A. Kumagai, S. Kanai, N. Ueda,
    Fast and Accurate Anchor Graph-based Label Prediction,
    International Conference on Information and Knowledge Management (CIKM), 2021.

  12. D. Chijiwa, S. Yamaguchi, Y. Ida, K. Umakoshi, T. Inoue,
    Pruning Randomly Initialized Neural Networks with Iterative Randomization,
    Neural Information Processing Systems (NeurIPS, spotlight), 2021.
    [paper]

  13. S. Kanai, M. Yamada, S. Yamaguchi, H. Takahashi, Y. Ida,
    Constraining Logits by Bounded Function for Adversarial Robustness,
    International Joint Conference on Neural Networks (IJCNN), 2021.

  14. Y. Fujiwara, Y. Ida, S, Kanai, A. Kumagai, N. Ueda,
    Fast Similarity Computation for t-SNE,
    IEEE International Conference on Data Engineering (ICDE), 2021.

  15. Y. Ida, S. Kanai, Y. Fujiwara, T. Iwata, K. Takeuchi, H. Kashima,
    Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance,
    International Conference on Machine Learning (ICML), 2020.
    [paper] [slide]

  16. Y. Fujiwara, A. Kumagai, S. Kanai, Y. Ida, T. Kawanishi, N. Ueda
    Efficient Algorithm for the b-Matching Graph,
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020.
    [paper]

  17. Y. Ida, Y. Fujiwara,
    Improving Generalization Performance of Adaptive Learning Rate by Switching from Block Diagonal Matrix Preconditioning to SGD,
    International Joint Conference on Neural Networks (IJCNN), 2020.
    [paper]

  18. S. Kanai, Y. Ida, Y. Fujiwara, M. Yamada, S. Adachi,
    Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks,
    Association for the Advancement of Artificial Intelligence (AAAI), 2020.
    [paper(pdf)]

  19. Y. Ida, Y. Fujiwara, H. Kashima,
    Fast Sparse Group Lasso,
    Neural Information Processing Systems (NeurIPS), 2019.
    [paper] [slide]

  20. Y. Fujiwara, Y. Ida, S. Kanai, A. Kumagai, J. Arai, N. Ueda,
    Fast Random Forest Algorithm via Incremental Upper Bound,
    International Conference on Information and Knowledge Management (CIKM), 2019.

  21. Y. Fujiwara, S. Kanai, J. Arai, Y. Ida, N. Ueda,
    Efficient Data Point Pruning for One-Class SVM,
    Association for the Advancement of Artificial Intelligence (AAAI), 2019.

  22. Y. Ida, Y. Fujiwara,
    Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining,
    International Joint Conference on Neural Networks (IJCNN), 2019.
    [paper]

  23. Y. Fujiwara, J. Arai, S. Kanai, Y. Ida, N. Ueda,
    Adaptive Data Pruning for Support Vector Machines,
    IEEE BigData, 2018.

  24. Y. Ida, Y. Fujiwara, S. Iwamura,
    Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks,
    International Joint Conference on Artificial Intelligence (IJCAI), 2017.
    [paper] [slide]

  25. Y. Fujiwara, Y. Ida, H. Shiokawa, S. Iwamura,
    Fast Lasso Algorithm via Selective Coordinate Descent,
    Association for the Advancement of Artificial Intelligence (AAAI), 2016.

  26. Y. Fujiwara, M. Nakatsuji, Y. Ida, M. Toyoda,
    Adaptive Message Update for Fast Affinity Propagation,
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2016.

  27. Y. Ida, T. Nakamura, T. Matsumoto,
    Domain-Dependent/Independent Topic Switching Model for Online Reviews with Numerical Ratings,
    ACM International Conference on Information and Knowledge Management (CIKM), 2013.
    [paper]

  28. H. Miyashita, T. Suzuki, T. Nakamura, Y. Ida, Takashi Matsumoto, T. Kaburagi
    Nonparametric Bayes-based Heterogeneous "Drosophila melanogaster" Gene Regulatory Network Inference: T-Process Regression,
    Artificial Intelligence and Applications (AIA), 2013. Best Student Paper Award.

  29. T. Suzuki, T. Nakamura, Y. Ida, T. Matsumoto
    Handling Incomplete Matrix Data Via Continuous-Valued Infinite Relational Model,
    International Conference on Acoustic, Speech, and Signal Processing (ICASSP), 2012.


International Journal Papers

  1. Y. Fujiwara, Y. Ida, A. Kumagai, M. Nakano, A. Kimura, N. Ueda,
    Efficient Network Representation Learning via Cluster Similarity,
    Data Science and Engineering (DSE), 2023.
    [paper(pdf)]

  2. S. Kanai, M. Yamada, H. Takahashi, Y. Yamanaka, Y. Ida,
    Relationship between Non-smoothness in Adversarial Training, Constraints of Attacks, and Flatness in the Input Space,
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023.
    [paper(pdf)]

  3. Y. Fujiwara, S. Kanai, Y. Ida, A. Kumagai, N. Ueda,
    Fast Algorithm for Anchor Graph Hashing,
    Proceedings of the Very Large Data Bases (PVLDB), 2021.
    [paper(pdf)]

  4. Y. Fujiwara, Y. Ida, J. Arai, M. Nishimura, S. Iwamura,
    Fast Algorithm for the Lasso based L1-Graph Construction,
    Proceedings of the Very Large Data Bases (PVLDB), 2016.
    [paper]

  5. Y. Fukuda, Y. Ida, T. Matsumoto, N. Takemura, S. Kaoru,
    A Bayesian Algorithm for Anxiety Index Prediction Based on CerebralBlood Oxygenation in the Prefrontal Cortex Measured by Near Infrared Spectroscopy,
    IEEE Journal of Translational Engineering in Health and Medicine (JTEHM), 2014.
    [paper]


Domestic Journal Papers

  1. Y. Ida, Y. Fujiwara, H. Kashima,
    Fast Block Coordinate Descent for Sparse Group Lasso,
    The Japanese Society for Artificial Intelligence, Vol. 36, No. 1, pp. A-JB1_1-11, 2021.
    [paper]

  2. Y. Ida, Y. Fujiwara,
    Model Compression for ResNet via Layer Erasure and Re-training,
    The Japanese Society for Artificial Intelligence, Vol. 35, No. 3, pp. C-JA3_1-10, 2020.
    [paper]


International Workshop Papers

  1. Y. Ida, T. Nakamura, T. Matsumoto,
    Label-Related/Unrelated Topic Switching Model: A Partially Labeled Topic Model Handling Infinite Label-unrelated Topics,
    Recent Advances in Computer Vision and Pattern Recognition (RACVPR, Workshop on ACPR), 2013.

Work Experience


  • Apr. 2022 -
    Distinguished Researcher, NTT Computer and Data Science Laboratories, Nippon Telegraph and Telephone Corporation (NTT), Japan
  • Jul. 2021 - Mar. 2022
    Researcher, NTT Computer and Data Science Laboratories, Nippon Telegraph and Telephone Corporation (NTT), Japan
  • Apr. 2014 - Jun. 2021
    Researcher, NTT Software Innovation Center, Nippon Telegraph and Telephone Corporation (NTT), Japan
  • 2012 - Mar. 2014
    Engineer (part-time), JX PRESS Corp., Japan
  • July 2012 - Sept. 2012
    Intern, Akihabara Lab., CyberAgent, Inc., Japan

Education


  • Mar. 2021: Ph.D.
    • Kyoto University, Japan
    • Supervisor: Prof. Hisashi Kashima
  • Mar. 2014: M.Eng
    • Waseda University, Japan
    • Supervisor: Prof. Takashi Matsumoto
  • Mar. 2012: B.Eng
    • Waseda University, Japan
    • Supervisor: Prof. Takashi Matsumoto

Educational Work Experience


  • Nov. 2016 - Feb. 2018
    Guest lecturer, Suwa University of Science, Japan
  • Oct. 2011 - Mar. 2013
    Teaching-Assistant, Waseda University, Japan

Activities


Organizing Committee

  • PAKDD2023, Registration Chair.

SPC

  • IJCAI: 2021.

Reviewer

  • NeurIPS: 2016, 2020, 2024.
  • ICML: 2020, 2021, 2022 (Top 10% reviewer).
  • IJCAI: 2020, 2021, 2022, 2024.
  • AAAI: 2020, 2021, 2023.
  • AISTATS: 2023.