Koh Takeuchi
News
Profile / CV
2009年 早稲田大学理工学部電気・情報生命工学科卒業
2011年 同大学大学院 修士課程修了
2019年 京都大学 大学院情報学研究科 知能情報学専攻 博士後期課程 修了， 博士（情報学）
職歴
2011年 日本電信電話株式会社入社
2020年 京都大学 大学院情報学研究科 知能情報学専攻 助教
2020年- JST さきがけ 信頼されるAI領域 1期生 (兼任)
Publications
List of released publications
Xiaofeng Lin, Guoxi Zhang, Xiaotian Lu, Han Bao, Koh Takeuchi, Hisashi Kashima.
Estimating Treatment Effects Under Heterogeneous Interference.
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2023.
# 複数種類の関係をもつグラフ上での介入効果推定手法を提案
Ryu Shirakami, Toshiya Kitahara, Koh Takeuchi, Hisashi Kashima.
“QTNet: Theory-based Queue Length Prediction for Urban Traffic,”
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023.
# 交通工学理論に基づくQueueing-theory-based Neural Network (QT-Net)を提案し、東京都交通網における渋滞長予測を高精度化した。
Koh Takeuchi, Ryo Nishida, Hisashi Kashima, Masaki Onishi.
Causal Effect Estimation on Hierarchical Spatial Graph Data.
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023.
# 階層的な空間グラフデータから因果効果を推定するSpatial Intervention Neural Network (SINet) を提案した。
Ryyosuke Ueda, Koh Takeuchi, Hisashi Kashima.
Fair Opinion Aggregation for Voter Attribute Bias.
In Proceedings of 6th AAAI/ACM Conference on AI, Ethics, and Society (AIES), 2023.
# 属性の偏った集団において、公平な意見統合を行う手法を提案
Xiotioan Lu, Jiyi Li, Koh Takeuchi, Hisashi Kashima.
Multiview Representation Learning from Crowdsourced Triplet Comparisons.
In Proceedings of the Web Conference (WWW), 2023.
# クラウドソーシングで収集した類似度比較データから様々な視点での表現を獲得する手法を提案
R. Ueda, K. Takeuchi, H. Kashima.
Mitigating Observation Biases in Crowdsourced Label Aggregation.
In Proceedings of the 26th International Conference on Pattern Recognition (ICPR), 2022.
# クラウドソーシングの回答に観測バイアスが存在する場合の回答統合手法を提案
兒玉 庸平, 朱山 裕宜, 宮崎 祐丞, 竹内 孝.
“(AI・データサイエンス奨励賞) 非線形教師あり学習による地理空間情報とIC定期データからの駅周辺における商圏人口分析,”
土木学会 構造工学委員会, 2022.
Sein Minn, Jill-Jenn Vie, Koh Takeuchi, Hisashi Kashima, Feida Zhu.
Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations.
In Proceedings of the 12th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI), 2022.
# eラーニング上の生徒の習熟度を特徴量構造の発見によって推定する手法を提案
Naoya Takeishi, Keisuke Fujii, Koh Takeuchi, Yoshinobu Kawahara.”Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections”SIAM Journal on Applied Dynamical Systems (SIADS), 2022.
N. Takeishi, K. Fujii, K. Takeuchi, Y. Kawahara.”Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections”SIAM Journal on Applied Dynamical Systems (SIADS), 2022.
第35回全国大会優秀賞, 因果推論を用いた群衆移動の誘導における介入効果推定, 人工知能学会
竹内 孝, 西田 遼, 鹿島 久嗣, 大西 正輝
K. Takeuchi, M. Imaizumi, S. Kanda, K. Fujii ,M. Ishihata, T. Maekawa, K. Yoda, Y. Tabei.”Fréchet Kernel for Trajectory Data Analysis”In Proceedings of 29th ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2021.
L. Xiaotian, A. Tolmachev, T. Yamamoto, K. Takeuchi, S. Okajima, T. Takebayashi, K. Maruhashi, H. Kashima.”Crowdsourcing Evaluation of Saliency-based XAI Methods”In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2021.
L. Phuc, K. Takeuchi, S. Okajima, A. Tolmachev, T. Takebayashi, K. Maruhashi, H. Kashima.”Inter-domain Multi-relational Link Prediction”In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2021.
S. Nakamura, K. Takeuchi, H. Kashima, T. Kishikawa, T. Ushio, T. Haga, T. Sasaki.”In-Vehicle Network Attack Detection Across Vehicle Models: A Supervised-Unsupervised Hybrid Approach”In Proceedings of the 24th IEEE International Intelligent Transportation Systems Conference (ITSC), 2021.
K. Takeuchi, R. Nishida, H. Kashima, M. Onishi”Grab the Reins of Crowds: Estimating the Effects of Crowd Movement Guidance Using Causal Inference”In Proceedings of 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021.
Koh Takeuchi, Yoshinobu Kawahara, Tomoharu Iwata.
“Structurally Regularized Non-negative Tensor Factorization for Spatio-Temporal Pattern Discoveries,”
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2017
竹内 孝, 西田 遼, 鹿島 久嗣, 大西 正輝 “第35回全国大会優秀賞 因果推論を用いた群衆移動の誘導における介入効果推定 人工知能学会”
S. Maekawa, K. Takeuchi, M. Onizuka”New Attributed Graph Clustering by Bridging Attribute and Topology Spaces”In Proceedings of the 28th,2020
Y. Ogawa, K. Takeuchi, Y. Sasaki 0001, M. Onizuka”Proximity Preserving Nonnegative Matrix Factorization”In Proceedings of the 28th,2020.
Y. Ida, S. Kanai,Y. Fujiwara, T. Iwata, K. Takeuchi, H. Kashima.”Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance”In Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.
L. Phuc, K. Takeuchi, M. Yamada, H. Kashima.”Simultaneous Link Prediction on Unaligned Networks Using Graph Embedding and Optimal Transport”In Proceedings of the the 7th IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2020.
Naoya Takeishi, Keisuke Fujii, Koh Takeuchi, Yoshinobu Kawahara.”Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections”SIAM Journal on Applied Dynamical Systems (SIADS), 2022.
岸野 泰恵, 白井 良成, 水谷 伸, 竹内 孝, 須山 敬之, 納谷 太, 上田 修功.”第63回優秀論文賞 ゴミ収集車に搭載したセンサを用いた状況識別による地区別ゴミ量推定と地区特性の分析 UBI研究会”
越塚 毅, 竹内 孝, 松林 達史, 澤田 宏.”最優秀論文賞 グラフを用いたNMFの地域分散高速化 DICOMO”
Akisato Kimura, Zoubin Ghahramani, Koh Takeuchi, Tomoharu Iwata, Naonori Ueda.
“Few-shot learning of neural networks from scratch by pseudo example optimization.”
In Proceedings of the British Machine Vision Conference (BMVC), 2018.
Motoyuki Oki, Koh Takeuchi, Yukio Uematsu.
“Mobile Network Failure Event Detection and Forecasting With Multiple User Activity Data Sets.”
In Proceedings of the AAAI Conference on Artificial Intelligence, 2018
米澤 拓郎, 伊藤 友隆, 坂村 美奈, 竹内 孝, 納谷 太, 上田 修功, 中澤 仁.”優秀論文賞 自治体職員参加型センシングによる業務効率化と都市理解の向上 DICOMO2018″
Makoto Yamada, Koh Takeuchi, Tomoharu Iwata, John Shawe-Taylor, Samuel Kaski.
“Localized Lasso for High-Dimensional Regression.”
In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017.
Koh Takeuchi, Hisashi Kashima, Naonori Ueda
“Autoregressive Tensor Factorization for Spatio-Temporal Predictions.”
In Proceedings of 2017 IEEE International Conference on Data Mining (ICDM), 2017
Yasuhiro Fujiwara, Naoki Marumo, Mathieu Blondel, Koh Takeuchi, Hideaki Kim, Tomoharu Iwata, Naonori Ueda.
“SVD-Based Screening for the Graphical Lasso.”
In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI), 2017.
Koh Takeuchi, Yoshinobu Kawahara, Tomoharu Iwata
“Higher Order Fused Regularization for Supervised Learning with Grouped Parameters.”
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2015.
Tomoharu Iwata, Koh Takeuchi.
“Cross-domain recommendation without shared users or items by sharing latent vector distributions.”
In Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics (AISTATS), 2015.
竹内 孝,河原 吉伸,岩田 具治.”2015年度人工知能学会研究会優秀賞 高階結合正則化による時空間変化パターン検出 人工知能学会”
竹内 孝, 石黒 勝彦, 小林 哲生, 藤田早苗, 平 博順.”第28回人工知能学会全国大会優秀賞 複合非負値行列因子分解(NM2F)による絵本デー タセットからの多角的パターン抽出 人工知能学会”
竹内 孝.”コミュニケーション科学基礎研究所奨励賞 NTT”
Koh Takeuchi, Ryota Tomioka, Katsuhiko Ishiguro, Akisato Kimura, Hiroshi Sawada
“Non-negative Multiple Tensor Factorization.”
In Proceeding of IEEE 13th International Conference on Data Mining(ICDM), 2013.
Koh Takeuchi, Katsuhiko Ishiguro, Akisato Kimura, Hiroshi Sawada.
“Non-Negative Multiple Matrix Factorization.”
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI), 2013.
竹内 孝,石黒 勝彦,木村 昭悟,澤田 宏.”研究発表会ベストプレゼンテーション賞 非負制約下における複合行列分解 数理モデル化と問題解決研究会”
Katsuhiko Ishiguro, Akisato Kimura, Koh Takeuchi.
“Towards Automatic Image Understanding and Mining via Social Curation.”
In Proceedings of 12th IEEE International Conference on Data Mining(ICDM), 2012.
竹内 孝, 石黒 勝彦, 木村 昭悟, 澤田 宏.”ポスター奨励賞 sNMF:非負値制約下における複数行列の同時分解法 ~ソ ーシャルメディア解析を応用例として~ 第16回情報論的学習理論ワークショップ
Xiaofeng Lin, Guoxi Zhang, Xiaotian Lu, Han Bao, Koh Takeuchi, Hisashi Kashima.
Estimating Treatment Effects Under Heterogeneous Interference.
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2023.
# 複数種類の関係をもつグラフ上での介入効果推定手法を提案
Ryu Shirakami, Toshiya Kitahara, Koh Takeuchi, Hisashi Kashima.
“QTNet: Theory-based Queue Length Prediction for Urban Traffic,”
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023.
# 交通工学理論に基づくQueueing-theory-based Neural Network (QT-Net)を提案し、東京都交通網における渋滞長予測を高精度化した。
Koh Takeuchi, Ryo Nishida, Hisashi Kashima, Masaki Onishi.
Causal Effect Estimation on Hierarchical Spatial Graph Data.
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023.
# 階層的な空間グラフデータから因果効果を推定するSpatial Intervention Neural Network (SINet) を提案した。
Ryyosuke Ueda, Koh Takeuchi, Hisashi Kashima.
Fair Opinion Aggregation for Voter Attribute Bias.
In Proceedings of 6th AAAI/ACM Conference on AI, Ethics, and Society (AIES), 2023.
# 属性の偏った集団において、公平な意見統合を行う手法を提案
Xiotioan Lu, Jiyi Li, Koh Takeuchi, Hisashi Kashima.
Multiview Representation Learning from Crowdsourced Triplet Comparisons.
In Proceedings of the Web Conference (WWW), 2023.
# クラウドソーシングで収集した類似度比較データから様々な視点での表現を獲得する手法を提案
R. Ueda, K. Takeuchi, H. Kashima.
Mitigating Observation Biases in Crowdsourced Label Aggregation.
In Proceedings of the 26th International Conference on Pattern Recognition (ICPR), 2022.
# クラウドソーシングの回答に観測バイアスが存在する場合の回答統合手法を提案
Sein Minn, Jill-Jenn Vie, Koh Takeuchi, Hisashi Kashima, Feida Zhu.
Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations.
In Proceedings of the 12th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI), 2022.
# eラーニング上の生徒の習熟度を特徴量構造の発見によって推定する手法を提案
N. Takeishi, K. Fujii, K. Takeuchi, Y. Kawahara.”Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections”SIAM Journal on Applied Dynamical Systems (SIADS), 2022.
K. Takeuchi, M. Imaizumi, S. Kanda, K. Fujii ,M. Ishihata, T. Maekawa, K. Yoda, Y. Tabei.”Fréchet Kernel for Trajectory Data Analysis”In Proceedings of 29th ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2021.
L. Xiaotian, A. Tolmachev, T. Yamamoto, K. Takeuchi, S. Okajima, T. Takebayashi, K. Maruhashi, H. Kashima.”Crowdsourcing Evaluation of Saliency-based XAI Methods”In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2021.
L. Phuc, K. Takeuchi, S. Okajima, A. Tolmachev, T. Takebayashi, K. Maruhashi, H. Kashima.”Inter-domain Multi-relational Link Prediction”In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2021.
S. Nakamura, K. Takeuchi, H. Kashima, T. Kishikawa, T. Ushio, T. Haga, T. Sasaki.”In-Vehicle Network Attack Detection Across Vehicle Models: A Supervised-Unsupervised Hybrid Approach”In Proceedings of the 24th IEEE International Intelligent Transportation Systems Conference (ITSC), 2021.
K. Takeuchi, R. Nishida, H. Kashima, M. Onishi”Grab the Reins of Crowds: Estimating the Effects of Crowd Movement Guidance Using Causal Inference”In Proceedings of 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021.
Koh Takeuchi, Yoshinobu Kawahara, Tomoharu Iwata.
“Structurally Regularized Non-negative Tensor Factorization for Spatio-Temporal Pattern Discoveries,”
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2017
S. Maekawa, K. Takeuchi, M. Onizuka”New Attributed Graph Clustering by Bridging Attribute and Topology Spaces”In Proceedings of the 28th,2020
Y. Ogawa, K. Takeuchi, Y. Sasaki 0001, M. Onizuka”Proximity Preserving Nonnegative Matrix Factorization”In Proceedings of the 28th,2020.
Y. Ida, S. Kanai,Y. Fujiwara, T. Iwata, K. Takeuchi, H. Kashima.”Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance”In Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.
L. Phuc, K. Takeuchi, M. Yamada, H. Kashima.”Simultaneous Link Prediction on Unaligned Networks Using Graph Embedding and Optimal Transport”In Proceedings of the the 7th IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2020.
Naoya Takeishi, Keisuke Fujii, Koh Takeuchi, Yoshinobu Kawahara.”Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections”SIAM Journal on Applied Dynamical Systems (SIADS), 2022.
Akisato Kimura, Zoubin Ghahramani, Koh Takeuchi, Tomoharu Iwata, Naonori Ueda.
“Few-shot learning of neural networks from scratch by pseudo example optimization.”
In Proceedings of the British Machine Vision Conference (BMVC), 2018.
Motoyuki Oki, Koh Takeuchi, Yukio Uematsu.
“Mobile Network Failure Event Detection and Forecasting With Multiple User Activity Data Sets.”
In Proceedings of the AAAI Conference on Artificial Intelligence, 2018
Makoto Yamada, Koh Takeuchi, Tomoharu Iwata, John Shawe-Taylor, Samuel Kaski.
“Localized Lasso for High-Dimensional Regression.”
In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017.
Koh Takeuchi, Hisashi Kashima, Naonori Ueda
“Autoregressive Tensor Factorization for Spatio-Temporal Predictions.”
In Proceedings of 2017 IEEE International Conference on Data Mining (ICDM), 2017
Yasuhiro Fujiwara, Naoki Marumo, Mathieu Blondel, Koh Takeuchi, Hideaki Kim, Tomoharu Iwata, Naonori Ueda.
“SVD-Based Screening for the Graphical Lasso.”
In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI), 2017.
第35回全国大会優秀賞, 因果推論を用いた群衆移動の誘導における介入効果推定, 人工知能学会
竹内 孝, 西田 遼, 鹿島 久嗣, 大西 正輝
竹内 孝, 西田 遼, 鹿島 久嗣, 大西 正輝 “第35回全国大会優秀賞 因果推論を用いた群衆移動の誘導における介入効果推定 人工知能学会”
岸野 泰恵, 白井 良成, 水谷 伸, 竹内 孝, 須山 敬之, 納谷 太, 上田 修功.”第63回優秀論文賞 ゴミ収集車に搭載したセンサを用いた状況識別による地区別ゴミ量推定と地区特性の分析 UBI研究会”
越塚 毅, 竹内 孝, 松林 達史, 澤田 宏.”最優秀論文賞 グラフを用いたNMFの地域分散高速化 DICOMO”
米澤 拓郎, 伊藤 友隆, 坂村 美奈, 竹内 孝, 納谷 太, 上田 修功, 中澤 仁.”優秀論文賞 自治体職員参加型センシングによる業務効率化と都市理解の向上 DICOMO2018″
竹内 孝,河原 吉伸,岩田 具治.”2015年度人工知能学会研究会優秀賞 高階結合正則化による時空間変化パターン検出 人工知能学会”
竹内 孝, 石黒 勝彦, 小林 哲生, 藤田早苗, 平 博順.”第28回人工知能学会全国大会優秀賞 複合非負値行列因子分解(NM2F)による絵本デー タセットからの多角的パターン抽出 人工知能学会”
竹内 孝.”コミュニケーション科学基礎研究所奨励賞 NTT”
竹内 孝,石黒 勝彦,木村 昭悟,澤田 宏.”研究発表会ベストプレゼンテーション賞 非負制約下における複合行列分解 数理モデル化と問題解決研究会”
竹内 孝, 石黒 勝彦, 木村 昭悟, 澤田 宏.”ポスター奨励賞 sNMF:非負値制約下における複数行列の同時分解法 ~ソ ーシャルメディア解析を応用例として~ 第16回情報論的学習理論ワークショップ
Get In Touch
