3 Hits in 1.8 sec

GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks [article]

Zhihua Jin, Yong Wang, Qianwen Wang, Yao Ming, Tengfei Ma, Huamin Qu
2022 arXiv   pre-print
It is therefore difficult to diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs and RNNs, little research has addressed the challenges for GNNs.  ...  However, similar to other deep neural networks like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), GNNs behave like a black box with their details hidden from model developers  ...  We also thank the anonymous reviewers for their detailed reviews and constructive suggestions.  ... 
arXiv:2011.11048v6 fatcat:advjnbjkfzgyzlhla3ydvebney

Black-box error diagnosis in deep neural networks: a survey of tools [article]

Piero Fraternali, Federico Milani, Rocio Nahime Torres, Niccolò Zangrando
2022 arXiv   pre-print
The application of Deep Neural Networks (DNNs) to a broad variety of tasks demands methods for coping with the complex and opaque nature of these architectures.  ...  Such performance-driven meta-annotations enable the detailed characterization of performance metrics and errors and help scientists identify the features of the input responsible for prediction failures  ...  ACKNOWLEDGMENTS This work is partially supported by the project "PRECEPT -A novel decentralized edge-enabled PREsCriptivE and Proac-Tive framework for increased energy efficiency and well-being in residential  ... 
arXiv:2201.06444v1 fatcat:2uvn2slp6vdgjild2oubrxvnta

Deep Visual Analytics (DVA): Applications, Challenges and Future Directions

Md Rafiqul Islam, Shanjita Akter, Md Rakybuzzaman Ratan, Abu Raihan M. Kamal, Guandong Xu
2021 Human-Centric Intelligent Systems  
Deep visual analytics visual analytics visual interactive system deep learning machine learning A B S T R A C T Visual interactive system (VIS) has been received significant attention for solving various  ...  While existing studies have applied various visual analytics (VA) to analyze and visualize insightful information, deep visual analytics (DVA) have considered as a promising technique to provide input  ...  neural network Chung et al. (2016) [20] Information analysis during training process [75] Discover vagueness of words Strobelt et al. (2017) [122] Hidden state analysiss Evermann et al.  ... 
doi:10.2991/hcis.k.210704.003 fatcat:wi2oxp66wvan7oc3rgumkvnl3m