Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Chen, Fanglan"'
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a re
Externí odkaz:
http://arxiv.org/abs/2306.02175
Spatial optimization problems (SOPs) are characterized by spatial relationships governing the decision variables, objectives, and/or constraint functions. In this article, we focus on a specific type of SOP called spatial partitioning, which is a com
Externí odkaz:
http://arxiv.org/abs/2208.02867
Recently, an increasing number of researchers, especially in the realm of political redistricting, have proposed sampling-based techniques to generate a subset of plans from the vast space of districting plans. These techniques have been increasingly
Externí odkaz:
http://arxiv.org/abs/2206.03703
Urban planning refers to the efforts of designing land-use configurations given a region. However, to obtain effective urban plans, urban experts have to spend much time and effort analyzing sophisticated planning constraints based on domain knowledg
Externí odkaz:
http://arxiv.org/abs/2112.14699
Autor:
Roy, Padmaksha, Sarkar, Shailik, Biswas, Subhodip, Chen, Fanglan, Chen, Zhiqian, Ramakrishnan, Naren, Lu, Chang-Tien
Publikováno v:
Published as conference paper at ASONAM 2021, Research Track
Modeling the spatiotemporal nature of the spread of infectious diseases can provide useful intuition in understanding the time-varying aspect of the disease spread and the underlying complex spatial dependency observed in people's mobility patterns.
Externí odkaz:
http://arxiv.org/abs/2111.05199
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Autor:
Chen, Zhiqian, Chen, Fanglan, Zhang, Lei, Ji, Taoran, Fu, Kaiqun, Zhao, Liang, Chen, Feng, Wu, Lingfei, Aggarwal, Charu, Lu, Chang-Tien
Deep learning's performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. Since most GNNs were created using distinct theori
Externí odkaz:
http://arxiv.org/abs/2107.10234
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations. Recent progress in fewshot semantic segme
Externí odkaz:
http://arxiv.org/abs/2007.01496
Autor:
Chen, Zhiqian, Chen, Fanglan, Zhang, Lei, Ji, Taoran, Fu, Kaiqun, Zhao, Liang, Chen, Feng, Wu, Lingfei, Aggarwal, Charu, Lu, Chang-Tien
Deep learning's success has been widely recognized in a variety of machine learning tasks, including image classification, audio recognition, and natural language processing. As an extension of deep learning beyond these domains, graph neural network
Externí odkaz:
http://arxiv.org/abs/2002.11867
Autor:
Chen, Zhiqian1 (AUTHOR) zchen@cse.msstate.edu, Chen, Fanglan2 (AUTHOR) fanglanc@vt.edu, Zhang, Lei2 (AUTHOR) zhanglei@vt.edu, Ji, Taoran3 (AUTHOR) taoran.ji@tamucc.edu, Fu, Kaiqun4 (AUTHOR) kaiqun.fu@sdstate.edu, Zhao, Liang5 (AUTHOR) liang.zhao@emory.edu, Chen, Feng6 (AUTHOR) feng.chen@utdallas.edu, Wu, Lingfei7 (AUTHOR) lwu@email.wm.edu, Aggarwal, Charu8 (AUTHOR) charu@us.ibm.com, Lu, Chang-Tien2 (AUTHOR) ctlu@vt.edu
Publikováno v:
ACM Computing Surveys. May2024, Vol. 56 Issue 5, p1-42. 42p.
The uncertainty measurement of classifiers' predictions is especially important in applications such as medical diagnoses that need to ensure limited human resources can focus on the most uncertain predictions returned by machine learning models. How
Externí odkaz:
http://arxiv.org/abs/1907.07590