機械学習，人工知能の分野では，国際会議は非常に重要な業績です．
AAAI, SIGIR, EMNLP, ECML/PKDD, COLINGは，人工知能，情報検索，自然言語処理，データマイニングにおけるトップ国際会議であり，採択が非常に厳しい会議です．

Journal Paper (Refereed)

• Investigating Word Vectors for the Negation of Verbs
  Tomoya Sasaki, Yuto Kikuchi, Kazuo Hara and Ikumi Suzuki
  SN computer Science, Vol.5, No. 222, Springer Nature, 2024.

• Study on visual machine-learning on the omnidirectional transporting robot

Adrian Zambrano, Kazuki Abe, Ikumi Suzuki, Theo Combelles, Kenjiro Tadakuma and Riichiro Tadakuma

Advanced Robotics, 34(13),(2020), pp.917-930

• Reducing Hub Translation Candidates Improves the Accuracy of. Bilingual Lexicon Extraction from Comparable Corpora
  Yutaro Shigeto, Ikumi Suzuki, Kazuo Hara, Masashi Shimbo and Yuji Matsumoto
  Journal of Japanese Society of Artificial Intelligence, Vol. 31, No.2  p.E-F43_1-12, 2016

• Computation of Contextual Word Similarity Exploiting Syntactic and SemanticStructural Co-occurrences
  Kazuo Hara, Ikumi Suzuki, Masashi Shimbo and Yuji Matsumoto
  Journal of Japanese Society of Artificial Intelligence, Vol.28, No.4, pp.379-390, 2013. (in Japanese)

• Reducing Hubs with Laplacian-based Kernels
  Ikumi Suzuki, Kazuo Hara, Masashi Shimbo and Yuji Matsumoto
  Journal of Japanese Society of Artificial Intelligence, Vol.28, No.3, pp.297-310, 2013. (in Japanese)

• Robust Model Selection for Classification of Microarrays.
  Ikumi Suzuki, Takashi Takenouchi, Miki Ohira, Shigeyuki Oba, and Shin Ishii.
  Cancer Informatics, Vol.7, pp.141-157, June 2009

International Conference/Workshop (Refereed)

• [AAAI 25] Hubness Change Point Detection
  Ikumi Suzuki, Kazuo Hara, Eiji Murakami
  In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI), pp. 12622-12630, Philadelphia, Pennsylvania, USA, (2025.3).

• [IEEE BigData 21] Bayesian Optimization With an Auxiliary Classifier for the Development of Polymer Materials.
  Tomoya Sasaki, Arisa Nakamura, Jun-Ichi Harasawa, Kazuo Hara, Ikumi Suzuki, Tatsuhiro Takahashi．
  2021 IEEE International Conference on Big Data (Big Data), pp. 6014-6016,  Orlando, FL, USA  (2021.12).

• [IEEE BigData 21] Robust Method to Convert HIRAGANA Sequences into Japanese Text.
  Toshiki Yamaguchi, Kazuo Hara, Ikumi Suzuki.
  2021 IEEE International Conference on Big Data (Big Data), pp.6058-6060,  Orlando, FL, USA  (2021.12).　

• [DATA 21] Impact of Duplicating Small Training Data On GANs
  Yuki Eizuka, Kazuo Hara, Ikumi Suzuki.
  In proceedings of 10th International Conference on Data Science, Technology and Applications (DATA 2021), pp.71-78, Online Streaming, (2021.7). 

• [DATA 21] Semantic Entanglement On Verb Negation
  Yuto Kikuchi, Kazuo Hara, Ikumi Suzuki.
  In proceedings of 10th International Conference on Data Science, Technology and Applications (DATA 2021), pp.71-78, Online Streaming, (2021.7).

• [KDIR 20] Target Evaluation for Neural Language Model using Japanese Case Frame
  Kazuhito Tamura, Ikumi Suzuki, Kazuo Hara
  In Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (KDIR 2020), pp 251-258, Budapest, Hungary, November 2-4, 2020

• [Romansy 20] Developing a Flexible Segment Unit for Redun-dant-DOF Manipulator using Bending Type Pneumatic Artificial Muscle
  Hiroki Tomori, Tomohiro Koyama, Hiromitsu Nishikata, Akinori Hayasaka and Ikumi Suzuki
  23rd CISM IFToMM Symposium on Robot Design, Dynamics and Control,pp.xxx-xxx, September 20-24, 2020 Sapporo, Japan

• [SIGIR 17] Centered kNN Graph for Semi-Supervised Learning
  Ikumi Suzuki and Kazuo Hara
  In proceedings of the 40th Annual ACM SIGIR Conference, pp.857-860, Tokyo 2017
  SIGIR is the top international conference in the field of Information Retrieval (IR). Accepted as a short paper, the acceptance rate is 30%)

• [AAAI 16] Flattening the Density Gradient for Eliminating Spatial Centrality to Reduce Hubness
  Kazuo Hara*, Ikumi Suzuki*, Kei Kobayashi, Kenji Fukumizu and Miloš Radovanović
  In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI), pp.1659-1665, Arizona, Phoenix, USA, February 2016.
  * Equally contributed  (AAAI is the top international conference in the field of Artificial Intelligence and Machine Learning. Accepted as a Full paper, the acceptance rate is 26%)

• [SISAP 15] Reducing Hubness for Kernel Regression
  Kazuo Hara, Ikumi Suzuki, Kei Kobayashi, Kenji Fukumizu and Miloš Radovanović
  In Proc. the 8th International Conference on Similarity Search and Applications (SISAP), pp.339-344, Glasgow, UK, 2015

• [SIGIR 15] Reducing Hubness: A Cause of Vulnerability in Recommender Systems
  Kazuo Hara, Ikumi Suzuki, Kei Kobayashi and Kenji Fukumizu
  In proceedings of the 38th Annual ACM SIGIR Conference, pp. 815-818, Santiago de Chile, August 2015
  SIGIR is the top international conference in the field of Information Retrieval (IR). Accepted as a short paper, the acceptance rate is 31%)

• [AAAI 15] Localized Centering: Reducing Hubness in Large-Sample Data.
  Kazuo Hara*, Ikumi Suzuki*, Masashi Shimbo, Kei Kobayashi, Kenji Fukumizu, Miloš Radovanović
  In Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI), pp.2645-2651, Texas, Austin, USA, January 2015
  * Equally contributed  (AAAI is the top international conference in the field of Artificial Intelligence and Machine Learning. Accepted as a Full paper, the acceptance rate is 26%)

• [ECML/PKDD 15] Ridge Regression, Hubness, and Zero-Shot Learning
  Yutaro Shigeto, Ikumi Suzuki, Kazuo Hara, Masashi Shimbo and Yuji Matsumoto
  In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pp.135-151, 2015. Acceptance rate 23%.

• [KDIR 14] Annotating Cohesive Statements of Anatomical Knowledge Toward Semi-automated Information Extraction
  Kazuo Hara, Ikumi Suzuki, Kousaku Okubo and Isamu Muto
  In Proceedings of the International Conference on Knowledge Discovery and Information Retrieval (KDIR), pp.342-347, Roma, Italy, October 2014

• [EMNLP 13] Centering Similarity Measures to Reduce Hubs
  Ikumi Suzuki, Kazuo Hara, Masashi Shimbo, Marco Saerens, Kenji Fukumizu
  In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Long Papers, pp.613-623, Seattle, USA, October, 2013.
  (EMNLP is the top international conference in the field of Natural Language Processing. Accepted as a Long Paper, the acceptance rate is 28%)

• [COLING 12] Walk-based Computation of Contextual Word Similarity    
  Kazuo Hara, Ikumi Suzuki, Masashi Shimbo, Yuji Matsumoto
  In Proceedings of the 24rd International Conference on Computational Linguistics (COLING). Mumbai, India, Long Papers(oral), pp.1081-1096, December 2012. 
  (COLING is the top international conference in the field of Natural Language Processing. Accepted as a Long paper, the acceptance rate is 25%)

• [AAAI 12] Investigating the Effectiveness of Laplacian-based Kernels in Hub Reduction
  Ikumi Suzuki, Kazuo Hara, Masashi Shimbo, Yuji Matsumoto, Marco Saerens
  In Proceedings of the 26th AAAI Conference on Artificial Intelligence (AAAI), pp.1112-1118, Toronto, Ontario, Canada, July 2012
  (AAAI is the top international conference in the field of Artificial Intelligence and Machine Learning. Accepted as a  Full paper, the acceptance rate is 26%)

• [DTMBIO 09] A Graph-based Approach for Biomedical Thesaurus Expansion
  Ikumi Suzuki, Kazuo Hara, Masashi Shimbo, and Yuji Matsumoto
  In Proceedings of the ACM Third International Workshop on Data and Text Mining in Bioinformatics (DTMBIO), Short Papers, pp.79-82. Hong Kong, November 2009

• [GIW 05] A Selection Criterion for Robust Classifiers: Cancer Prognosis with Microarray Gene Expression
  Ikumi Suzuki, Shigeyuki Oba, and Shin Ishii
  Genome Informatics Workshop (GIW), 2005