Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Atsutoshi Kumagai"'
Autor:
Yasuhiro Fujiwara, Yasutoshi Ida, Atsutoshi Kumagai, Masahiro Nakano, Akisato Kimura, Naonori Ueda
Publikováno v:
Data Science and Engineering, Vol 8, Iss 3, Pp 279-291 (2023)
Abstract Network representation learning is a de facto tool for graph analytics. The mainstream of the previous approaches is to factorize the proximity matrix between nodes. However, if n is the number of nodes, since the size of the proximity matri
Externí odkaz:
https://doaj.org/article/9f96328299044e299ef2c1e3deef884f
Publikováno v:
Data Science and Engineering, Vol 5, Iss 2, Pp 140-151 (2020)
Abstract We propose a transfer metric learning method to infer domain-specific data embeddings for unseen domains, from which no data are given in the training phase, by using knowledge transferred from related domains. When training and test distrib
Externí odkaz:
https://doaj.org/article/1189426fc9c24db98a792387b3a9bdf3
Autor:
Atsutoshi Kumagai
Publikováno v:
NTT Technical Review. 19:12-15
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c158724ad27722c0640b2bbb3303efe
https://doi.org/10.53829/ntr202112ri1
https://doi.org/10.53829/ntr202112ri1
Autor:
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Sekitoshi Kanai, Masanori Yamada, Yuuki Yamanaka, Hisashi Kashima
Publikováno v:
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c8faeae3fa29cfe7dcf94df91e52e2f
https://doi.org/10.1145/3534678.3539291
https://doi.org/10.1145/3534678.3539291
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fab7e492f6a0bcfc4679c6138aaa7976
https://doi.org/10.1109/ijcnn55064.2022.9892011
https://doi.org/10.1109/ijcnn55064.2022.9892011
Publikováno v:
Proceedings of the VLDB Endowment. 14:916-928
Anchor graph hashing is used in many applications such as cancer detection, web page classification, and drug discovery. It computes the hash codes from the eigenvectors of the matrix representing the similarities between data points and anchor point
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::08b4a6c60ae8d30edc73d7abca7cd393
https://doi.org/10.14778/3447689.3447696
https://doi.org/10.14778/3447689.3447696
Publikováno v:
Data Science and Engineering, Vol 5, Iss 2, Pp 140-151 (2020)
ICDM
ICDM
We propose a transfer metric learning method to infer domain-specific data embeddings for unseen domains, from which no data are given in the training phase, by using knowledge transferred from related domains. When training and test distributions ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c6eb7ba72a7d917f7ad6476e457f83d
https://doi.org/10.1007/s41019-020-00125-1
https://doi.org/10.1007/s41019-020-00125-1
Publikováno v:
CIKM
Anchor graphs are a popular tool used in label prediction of sparsely labeled data. In anchor graphs, labels of labeled data are propagated to unlabeled data via anchor points; anchor points are the centers of k-means clusters. Anchor graph-based lab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2b04f96132376411cbc2d5e44ad9c96
https://doi.org/10.1145/3459637.3482258
https://doi.org/10.1145/3459637.3482258
Publikováno v:
IJCNN
We propose a simple yet effective method for detecting anomalous instances on an attribute graph with label information of a small number of instances. Although with standard anomaly detection methods it is usually assumed that instances are independ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::608802d5fae092a7a60bdc1114e9165b
https://doi.org/10.1109/ijcnn52387.2021.9533507
https://doi.org/10.1109/ijcnn52387.2021.9533507
Autor:
Atsutoshi Kumagai, Tomoharu Iwata
Publikováno v:
AAAI
We propose a simple yet effective method for unsupervised domain adaptation. When training and test distributions are different, standard supervised learning methods perform poorly. Semi-supervised domain adaptation methods have been developed for th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1a2f2a1998f78118652a83bfb99f04d5
https://doi.org/10.1609/aaai.v33i01.33014106
https://doi.org/10.1609/aaai.v33i01.33014106