Zobrazeno 1 - 10
of 231
pro vyhledávání: '"LEI, Chuan"'
Autor:
Liang, Jiaming, Lei, Chuan, Qin, Xiao, Zhang, Jiani, Katsifodimos, Asterios, Faloutsos, Christos, Rangwala, Huzefa
Data-centric AI focuses on understanding and utilizing high-quality, relevant data in training machine learning (ML) models, thereby increasing the likelihood of producing accurate and useful results. Automatic feature augmentation, aiming to augment
Externí odkaz:
http://arxiv.org/abs/2406.09534
Autor:
Wang, Minjie, Gan, Quan, Wipf, David, Cai, Zhenkun, Li, Ning, Tang, Jianheng, Zhang, Yanlin, Zhang, Zizhao, Mao, Zunyao, Song, Yakun, Wang, Yanbo, Li, Jiahang, Zhang, Han, Yang, Guang, Qin, Xiao, Lei, Chuan, Zhang, Muhan, Zhang, Weinan, Faloutsos, Christos, Zhang, Zheng
Although RDBs store vast amounts of rich, informative data spread across interconnected tables, the progress of predictive machine learning models as applied to such tasks arguably falls well behind advances in other domains such as computer vision o
Externí odkaz:
http://arxiv.org/abs/2404.18209
Autor:
Koutras, Christos, Zhang, Jiani, Qin, Xiao, Lei, Chuan, Ioannidis, Vasileios, Faloutsos, Christos, Karypis, George, Katsifodimos, Asterios
How can we discover join relationships among columns of tabular data in a data repository? Can this be done effectively when metadata is missing? Traditional column matching works mainly rely on similarity measures based on exact value overlaps, henc
Externí odkaz:
http://arxiv.org/abs/2403.07653
Autor:
Kong, Kezhi, Zhang, Jiani, Shen, Zhengyuan, Srinivasan, Balasubramaniam, Lei, Chuan, Faloutsos, Christos, Rangwala, Huzefa, Karypis, George
Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use a retriever that fetches relevant
Externí odkaz:
http://arxiv.org/abs/2402.14361
Publikováno v:
Foundations and Trends in Databases 2022 Vol. 11: No. 4, pp 319-414
Recent advances in NLU and NLP have resulted in renewed interest in natural language interfaces to data, which provide an easy mechanism for non-technical users to access and query the data. While early systems evolved from keyword search and focused
Externí odkaz:
http://arxiv.org/abs/2212.13074
Publikováno v:
Zeitschrift für Kristallographie - New Crystal Structures, Vol 239, Iss 3, Pp 547-548 (2024)
C20H16FNO5, monoclinic, P21/c (no. 14), a = 9.5235(2) Å, b = 22.1323(2) Å, c = 8.95249(19) Å, β = 101.445(3)°, V = 1779.66(7) Å3, Z = 4, R gt(F) = 0.0410, wR ref(F 2) = 0.1194, T = 279.5 K.
Externí odkaz:
https://doaj.org/article/37508d7d27e84c94bc5a28763647957e
Developing scalable solutions for training Graph Neural Networks (GNNs) for link prediction tasks is challenging due to the high data dependencies which entail high computational cost and huge memory footprint. We propose a new method for scaling tra
Externí odkaz:
http://arxiv.org/abs/2201.02791
Publikováno v:
In Journal of Magnesium and Alloys May 2024 12(5):1799-1814
Publikováno v:
In Journal of Alloys and Compounds 5 March 2024 976
Conversational interfaces to Business Intelligence (BI) applications enable data analysis using a natural language dialog in small incremental steps. To truly unleash the power of conversational BI to democratize access to data, a system needs to pro
Externí odkaz:
http://arxiv.org/abs/2105.00467