Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Ian En-Hsu Yen"'
Publikováno v:
2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b4b45b011cf4f33845abfc9337637cf
https://doi.org/10.1109/dsaa54385.2022.10032353
https://doi.org/10.1109/dsaa54385.2022.10032353
Publikováno v:
Knowledge and Information Systems. 60:247-273
Modern retail chains, such as Starbucks and McDonald’s, seek for geographical locations that have higher possibility to bring the maximum profit to establish and open their new stores. For a retail store, the common indicator of profit is its popul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef4f1cb08155d42c3666509b2902933f
https://doi.org/10.1007/s10115-018-1311-x
https://doi.org/10.1007/s10115-018-1311-x
Publikováno v:
NAACL-HLT
Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large for resource
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a86ba8a6297d43db29d2ef59819b94ac
Autor:
Liang Ma, Ian En-Hsu Yen, Lingfei Wu, Liang Zhao, Charu C. Aggarwal, Siyu Huo, Kun Xu, Shouling Ji
Publikováno v:
KDD
Analysis of large-scale sequential data has been one of the most crucial tasks in areas such as bioinformatics, text, and audio mining. Existing string kernels, however, either (i) rely on local features of short substructures in the string, which ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eeb3706f26e923aed5377456d6a66b36
https://doi.org/10.1145/3292500.3330923
https://doi.org/10.1145/3292500.3330923
Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding
Autor:
Kun Xu, Zhen Zhang, Liang Zhao, Ian En-Hsu Yen, Lingfei Wu, Xi Peng, Charu C. Aggarwal, Yinglong Xia
Publikováno v:
KDD
Graph kernels are widely used for measuring the similarity between graphs. Many existing graph kernels, which focus on local patterns within graphs rather than their global properties, suffer from significant structure information loss when represent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec98689ae682f030d0f1898c502f1f19
Publikováno v:
KDD
Kernel method has been developed as one of the standard approaches for nonlinear learning, which however, does not scale to large data set due to its quadratic complexity in the number of samples. A number of kernel approximation methods have thus be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8cce10ac428ab436fc69bc76a3f659e0
http://arxiv.org/abs/1809.05247
http://arxiv.org/abs/1809.05247
Autor:
Fangli Xu, Pin-Yu Chen, Avinash Balakrishnan, Lingfei Wu, Michael Witbrock, Kun Xu, Pradeep Ravikumar, Ian En-Hsu Yen
Publikováno v:
EMNLP
While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fed19f7f63f29735f338d42b1c849d46
https://doi.org/10.18653/v1/d18-1482
https://doi.org/10.18653/v1/d18-1482
Publikováno v:
KDD
Extreme Classification comprises multi-class or multi-label prediction where there is a large number of classes, and is increasingly relevant to many real-world applications such as text and image tagging. In this setting, standard classification met
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a7235065665cb6093d55220d8736ae88
https://doi.org/10.1145/3097983.3098083
https://doi.org/10.1145/3097983.3098083
Publikováno v:
WWW
Online social networks nowadays enjoy their worldwide prosperity, as they have revolutionized the way for people to discover, to share, and to distribute information. With millions of registered users and the proliferation of user-generated contents,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::508ee37880bb4552d8f8242c14af5db3
https://doi.org/10.1145/2736277.2741673
https://doi.org/10.1145/2736277.2741673
Publikováno v:
KDD
Linear Classification has achieved complexity linear to the data size. However, in many applications, data contain large amount of samples that does not help improve the quality of model, but still cost much I/O and memory to process. In this paper,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4517fea97df3c94cb8604e0f4f815e9
https://doi.org/10.1145/2487575.2487626
https://doi.org/10.1145/2487575.2487626