Explore Your Network in Minutes: A Rapid Prototyping Toolkit for Understanding Neural Networks with Visual Analytics
Authors: 
Shaoxuan Lai, Wanna Luan, Jun TaoAuthors Info & Claims
Pages 683 - 693
Abstract
Neural networks attract significant attention in almost every field due to their widespread applications in various tasks. However, developers often struggle with debugging due to the black-box nature of neural networks. Visual analytics provides an intuitive way for developers to understand the hidden states and underlying complex transformations in neural networks. Existing visual analytics tools for neural networks have been demonstrated to be effective in providing useful hints for debugging certain network architectures. However, these approaches are often architecture-specific with strong assumptions of how the network should be understood. This limits their use when the network architecture or the exploration goal changes. In this paper, we present a general model and a programming toolkit, Neural Network Visualization Builder (NNVisBuilder), for prototyping visual analytics systems to understand neural networks. NNVisBuilder covers the common data transformation and interaction model involved in existing tools for exploring neural networks. It enables developers to customize a visual analytics interface for answering their specific questions about networks. NNVisBuilder is compatible with PyTorch so that developers can integrate the visualization code into their learning code seamlessly. We demonstrate the applicability by reproducing several existing visual analytics systems for networks with NNVisBuilder. The source code and some example cases can be found at <uri>https://github.com/sysuvis/NVB</uri>.
References
[1]
G. Alicioglu and B. Sun. A survey of visual analytics for explainable artificial intelligence methods. Computers & Graphics, 102: pp. 502–520, 2022. 1, 2.
[2]
S. Amershi, J. Fogarty, A. Kapoor, and D. Tan. Examining multiple potential models in End-User interactive concept learning. In Proceedings of SIGCHI Conference on Human Factors in Computing Systems, pp. 1357–1360. ACM, New York, 2010. 2.
[3]
M. Bostock, V. Ogievetsky, and J. Heer. D3 data-driven documents. IEEE Transactions on Visualization and Computer Graphics, 17 (12): pp. 2301–2309, 2011. 1, 2, 5, 9.
[4]
J. Chae, S. Gao, A. Ramanathan, C. A. Steed, and G. Tourassi. Visualization for Classification in Deep Neural Networks. In Workshop on Visual Analytics for Deep Learning. IEEE, October 2017. 2.
[5]
F. Cheng, Y. Ming, and H. Qu. DECE: Decision explorer with counter-factual explanations for machine learning models. IEEE Transactions on Visualization and Computer Graphics, 27 (2): pp. 1438–1447, 2021. 2, 3.
[6]
J. Choo and S. Liu. Visual analytics for explainable deep learning. IEEE Computer Graphics and Applications, 38 (4): pp. 84–92, 2018. 2.
[7]
S. Chung, S. Suh, C. Park, K. Kang, J. Choo, and B. C. Kwon. ReVACNN: Real-Time visual analytics for convolutional neural network. In Proceedings of ACM SIGKDD Workshop on Interactive Data Exploration and Analytics, vol. 14, 2016. 2.
[8]
N. Das, H. Park, Z. J. Wang, F. Hohman, R. Firstman, E. Rogers, and D. H. P. Chau. Bluff: Interactively deciphering adversarial attacks on deep neural networks. In Proceedings of IEEE Visualization Conference, pp. 271–275. IEEE, Salt Lake City, 2020. 2, 3.
[9]
D. Erhan, Y. Bengio, A. Courville, and P. Vincent. Visualizing higher-layer features of a deep network. Technical Report, Univeristé de Montréal, 1341 (3): pp. 1, 2009. 1, 2.
[10]
O. Gomez, S. Holter, J. Yuan, and E. Bertini. AdViCE: Aggregated visual counterfactual explanations for machine learning model validation. In Proceedings of IEEE Visualization Conference, pp. 31–35. IEEE, New Orleans, 2021. 2, 3.
[11]
A. W. Harley. An interactive Node-Link visualization of convolutional neural networks. In Proceedings of Advances in Visual Computing, pp. 867–877. Springer, Cham, 2015. 2.
[12]
F. Hohman, M. Kahng, R. Pienta, and D. H. Chau. Visual analytics in deep learning: An interrogative survey for the next frontiers. IEEE Transactions on Visualization and Computer Graphics, 25 (8): pp. 2674–2693, 2019. 1, 2.
[13]
B. Hoover, H. Strobelt, and S. Gehrmann. exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models. In Proceedings of Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 187–196. Association for Computational Linguistics, Online, July 2020. 2, 3.
[14]
J. D. Hunter. Matplotlib: A 2D graphics environment. Computing in Science & Engineering, 9 (03): pp. 90–95, 2007. 2.
[15]
Z. Jin, Y. Wang, Q. Wang, Y. Ming, T. Ma, and H. Qu. GNNLens: A visual analytics approach for prediction error diagnosis of graph neural networks. IEEE Transactions on Visualization and Computer Graphics, 29 (6): pp. 3024–3038, 2023. 2, 3.
[16]
A. Karpathy, J. Johnson, and L. Fei-Fei. Visualizing and Understanding Recurrent Networks. CoRR, abs/1506.02078, 2015. 2.
[17]
B. La Rosa, G. Blasilli, R. Bourqui, D. Auber, G. Santucci, R. Capobianco, E. Bertini, R. Giot, and M. Angelini. State of the art of visual analytics for explainable deep learning. Computer Graphics Forum, 42 (1): pp. 319–355, 2023. 1, 2.
[18]
J. K. Li and K.-L. Ma. P4: Portable parallel processing pipelines for interactive information visualization. IEEE Transactions on Visualization and Computer Graphics, 26 (3): pp. 1548–1561, 2020. 2.
[19]
J. K. Li and K.-L. Ma. P5: Portable progressive parallel processing pipelines for interactive data analysis and visualization. IEEE Transactions on Visualization and Computer Graphics, 26 (1): pp. 1151–1160, 2020. 2.
[20]
J. K. Li and K.-L. Ma. P6: A declarative language for integrating machine learning in visual analytics. IEEE Transactions on Visualization and Computer Graphics, 27 (2): pp. 380–389, 2021. 2.
[21]
Y. Li, J. Wang, T. Fujiwara, and K.-L. Ma. Visual analytics of neuron vulnerability to adversarial attacks on convolutional neural networks. ACM Transactions on Interactive Intelligent Systems, 2023. 2.
[22]
M. Liu, S. Liu, H. Su, K. Cao, and J. Zhu. Analyzing the noise robustness of deep neural networks. In Proceedings of IEEE Conference on Visual Analytics Science and Technology, pp. 60–71. IEEE, Berlin, 2018. 1, 2, 3.
[23]
M. Liu, J. Shi, Z. Li, C. Li, J. Zhu, and S. Liu. Towards better analysis of deep convolutional neural networks. IEEE Transactions on Visualization and Computer Graphics, 23 (1): pp. 91–100, 2017. 2, 3.
[24]
W. McKinney et al. pandas: a foundational python library for data analysis and statistics. Python for high performance and scientific computing, 14 (9): pp. 1–9, 2011. 6.
[25]
P. Migdal, J. Chapman, S. Paul, and R. Rv. torchviz: a package for neural network visualization and debugging. [Online]. Available: https://github.com/szagoruyko/pytorchviz, 2019. Accessed on: 2023-03-24. 1.
[26]
Y. Ming, S. Cao, R. Zhang, Z. Li, Y. Chen, Y. Song, and H. Qu. Understanding hidden memories of recurrent neural networks. In 2017 IEEE Conference on Visual Analytics Science and Technology, pp. 13–24. IEEE, Phoenix, 2017. 2, 3.
[27]
F. Ojo, R. A. Rossi, J. Hoffswell, S. Guo, F. Du, S. Kim, C. Xiao, and E. Koh. VisGNN: Personalized visualization recommendation via graph neural networks. In Proceedings of the ACM Web Conference, pp. 2810–2818. ACM, New York, 2022. 2.
[28]
J. G. S. Paiva, W. R. Schwartz, H. Pedrini, and R. Minghim. An approach to supporting incremental visual data classification. IEEE Transactions on Visualization and Computer Graphics, 21 (1): pp. 4–17, 2015. 2.
[29]
C. Park, S. Yang, I. Na, S. Chung, S. Shin, B. C. Kwon, D. Park, and J. Choo. VATUN: Visual Analytics for Testing and Understanding Convolutional Neural Networks. In Proceedings of EuroVis Short Papers. The Eurographics Association, 2021. 2.
[30]
A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Z. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala. PyTorch: An imperative style, high-performance deep learning library. In Proceedings of Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems, pp. 8024–8035, 2019. 5.
[31]
L. Roeder. Netron. Computer software, n.d. 1.
[32]
A. Satyanarayan, D. Moritz, K. Wongsuphasawat, and J. Heer. Vega-lite: A grammar of interactive graphics. IEEE Transactions on Visualization and Computer Graphics, 23 (1): pp. 341–350, 2017. 2.
[33]
A. Satyanarayan, R. Russell, J. Hoffswell, and J. Heer. Reactive vega: A streaming dataflow architecture for declarative interactive visualization. IEEE Transactions on Visualization and Computer Graphics, 22 (1): pp. 659–668, 2016. 2.
[34]
Q. Shen, Y. Wu, Y. Jiang, W. Zeng, A. K. H. Lau, A. Vianova, and H. Qu. Visual interpretation of recurrent neural network on multi-dimensional time-series forecast. In Proceedings of IEEE Pacific Visualization Symposium, pp. 61–70. IEEE, Tianjin, 2020. 2.
[35]
K. Simonyan, A. Vedaldi, and A. Zisserman. Deep inside convolutional networks: Visualising image classification models and saliency maps. In Y. Bengio and Y. LeCun, eds., Proceedings of International Conference on Learning Representations (Workshop), 2014. 1, 2.
[36]
D. Smilkov, N. Thorat, B. Kim, F. Viégas, and M. Wattenberg. TensorFlow Playground. [Online]. Available: https://playground.tensorflow.org/, 2017. 1, 2, 3, 7.
[37]
H. Strobelt, S. Gehrmann, M. Behrisch, A. Perer, H. Pfister, and A. M. Rush. Seq2seq-Vis: A visual debugging tool for sequence-to-sequence models. IEEE Transactions on Visualization and Computer Graphics, 25 (1): pp. 353–363, 2019. 1, 2, 3.
[38]
H. Strobelt, S. Gehrmann, H. Pfister, and A. M. Rush. LSTMVis: A tool for visual analysis of hidden state dynamics in recurrent neural networks. IEEE Transactions on Visualization and Computer Graphics, 24 (1): pp. 667–676, 2018. 1, 2, 3, 4.
[39]
G.-D. Sun, Y.-C. Wu, R.-H. Liang, and S.-X. Liu. A survey of visual analytics techniques and applications: State-of-the-art research and future challenges. Journal of Computer Science and Technology, 28: pp. 852–867, 2013. 2.
[40]
F.-Y. Tzeng and K.-L. Ma. Opening the black box - data driven visualization of neural networks. In Proceedings of IEEE Visualization, pp. 383–390. IEEE, Minneapolis, 2005. 2.
[41]
L. van der Maaten and G. Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, 9 (86): pp. 2579–2605, 2008. 2.
[42]
J. VanderPlas, B. E. Granger, J. Heer, D. Moritz, K. Wongsuphasawat, A. Satyanarayan, E. Lees, I. Timofeev, B. Welsh, and S. Sievert. Altair: Interactive Statistical Visualizations for Python. Journal of open source software, 3 (32): pp. 1057, 2018. 2.
[43]
J. Vig. A multiscale visualization of attention in the transformer model. CoRR, abs/1906.05714, 2019. 2.
[44]
J. Wang, L. Gou, H. Yang, and H.-W. Shen. GANViz: A visual analytics approach to understand the adversarial game. IEEE Transactions on Visualization and Computer Graphics, 24 (6): pp. 1905–1917, 2018. 1, 2, 3.
[45]
Z. J. Wang, R. Turko, and D. H. Chau. Dodrio: Exploring transformer models with interactive visualization. CoRR, abs/2103.14625, 2021. 2, 3.
[46]
Z. J. Wang, R. Turko, O. Shaikh, H. Park, N. Das, F. Hohman, M. Kahng, and D. H. Polo Chau. CNN explainer: Learning convolutional neural networks with interactive visualization. IEEE Transactions on Visualization and Computer Graphics, 27 (2): pp. 1396–1406, 2021. 2, 3.
[47]
H. Wickham. ggplot2. WIREs Computational Statistics, 3 (2): pp. 180–185, 2011. 2.
[48]
X. Xuan, X. Zhang, O.-H. Kwon, and K.-L. Ma. VAC-CNN: A visual analytics system for comparative studies of deep convolutional neural networks. IEEE Transactions on Visualization and Computer Graphics, 28 (6): pp. 2326–2337, 2022. 3.
[49]
J. Yosinski, J. Clune, A. M. Nguyen, T. J. Fuchs, and H. Lipson. Understanding neural networks through deep visualization. CoRR, abs/1506.06579, 2015. 1, 2.
[50]
J. Zhao, Z. Dai, P. Xu, and L. Ren. ProtoViewer: Visual interpretation and diagnostics of deep neural networks with factorized prototypes. In Proceedings of IEEE Visualization Conference, pp. 286–290. IEEE, Salt Lake City, 2020. 3.
Index Terms
- Explore Your Network in Minutes: A Rapid Prototyping Toolkit for Understanding Neural Networks with Visual Analytics
Index terms have been assigned to the content through auto-classification.
Recommendations
Granular neural networks
Fuzzy neural networks (FNNs) and rough neural networks (RNNs) both have been hot research topics in the artificial intelligence in recent years. The former imitates the human brain in dealing with problems, the other takes advantage of rough set theory ...
A new recurrent neural-network architecture for visual pattern recognition
We propose a new type of recurrent neural-network architecture, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units. The proposed recurrent neural network differs from Jordan's and ...
Energy efficient neural networks for big data analytics
DATE '14: Proceedings of the conference on Design, Automation & Test in EuropeThe world is experiencing a data revolution to discover knowledge in big data. Large scale neural networks are one of the mainstream tools of big data analytics. Processing big data with large scale neural networks includes two phases: the training ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
1077-2626 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Educational Activities Department
United States
Publication History
Published: 03 November 2023
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 13 Dec 2024