Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow

Wongsuphasawat, Kanit; Smilkov, Daniel; Wexler, James; Wilson, Jimbo; Mané, Dandelion; Fritz, Doug; Krishnan, Dilip; Viégas, Fernanda B.; Wattenberg, Martin

doi:10.1109/tvcg.2017.2744878

Cited by 270 publications

(171 citation statements)

References 33 publications

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“…More broadly, our work relates to the literature on visual analysis of neural networks (see [HKPC18] for a survey). Previous work has contributed techniques and systems to visualize hidden layers [ZF14,LSL∗17], training process [LSC∗18,PHVG∗18], model architecture [WSW∗18] and supervised learning results [RAL∗17]. Analyzing these aspects of the neural network are complementary to our focus on understanding latent spaces.…”

Section: Related Workmentioning

confidence: 99%

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Liu

Jun

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

Latent spaces—reduced‐dimensionality vector space embeddings of data, fit via machine learning—have been shown to capture interesting semantic properties and support data analysis and synthesis within a domain. Interpretation of latent spaces is challenging because prior knowledge, sometimes subtle and implicit, is essential to the process. We contribute methods for “latent space cartography”, the process of mapping and comparing meaningful semantic dimensions within latent spaces. We first perform a literature survey of relevant machine learning, natural language processing, and scientific research to distill common tasks and propose a workflow process. Next, we present an integrated visual analysis system for supporting this workflow, enabling users to discover, define, and verify meaningful relationships among data points, encoded within latent space dimensions. Three case studies demonstrate how users of our system can compare latent space variants in image generation, challenge existing findings on cancer transcriptomes, and assess a word embedding benchmark.

show abstract

Section: Related Workmentioning

confidence: 99%

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Liu

Jun

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Hohman et al [29] presented a comprehensive survey to summarize the state-of-the-art visual analysis methods for explainable deep learning. Existing methods can be categorized into three classes: network-centric [30], [31], [32], instance-centric [20], [33], [34], [35], and hybrid [36], [37]. Network-centric methods.…”

Section: Related Workmentioning

confidence: 99%

Analyzing the Noise Robustness of Deep Neural Networks

Cao

Liu

et al. 2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

A B C D E (a) Input images (b) Datapath visualization at the network-and layer-levels (c) Neuron visualization Figure 1: Explanation why an adversarial panda image is not classified as a panda. The root cause is identified as the neurons in the feature map F A failing to detect the outline of the panda's ear (E) in the adversarial example, which further leads to the failure of detecting the panda's ear (B) in F C1 . Abstract-Adversarial examples, generated by adding small but intentionally imperceptible perturbations to normal examples, can mislead deep neural networks (DNNs) to make incorrect predictions. Although much work has been done on both adversarial attack and defense, a fine-grained understanding of adversarial examples is still lacking. To address this issue, we present a visual analysis method to explain why adversarial examples are misclassified. The key is to compare and analyze the datapaths of both the adversarial and normal examples. A datapath is a group of critical neurons along with their connections. We formulate the datapath extraction as a subset selection problem and solve it by constructing and training a neural network. A multi-level visualization consisting of a network-level visualization of data flows, a layer-level visualization of feature maps, and a neuron-level visualization of learned features, has been designed to help investigate how datapaths of adversarial and normal examples diverge and merge in the prediction process. A quantitative evaluation and a case study were conducted to demonstrate the promise of our method to explain the misclassification of adversarial examples.

show abstract

“…The first component of a deep learning model that can be visualized is the computation/data flow graph. This aspect has been addressed by Wongsuphasawat et al [WSW∗18] in their work on TensorBoard for models that are specified in TensorFlow. The purpose of TensorBoard is supporting the user in understanding and debugging large computation graphs.…”

Section: Related Workmentioning

confidence: 99%

Visualization Support for Developing a Matrix Calculus Algorithm: A Case Study

Giesen

Klaus

Laue

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

The development of custom interactive visualization tools for specific domains and applications has been made much simpler recently by a surge of visualization tools, libraries and frameworks. Most of these tools are developed for classical data science applications, where a user is supported in analyzing measured or simulated data. But recently, there has also been an increasing interest in visual support for understanding machine learning algorithms and frameworks, especially for deep learning. Many, if not most, of the visualization support for (deep) learning addresses the developer of the learning system and not the end user (data scientist). Here we show on a specific example, namely the development of a matrix calculus algorithm, that supporting visualizations can also greatly benefit the development of algorithms in classical domains like in our case computer algebra. The idea is similar to visually supporting the understanding of learning algorithms, namely provide the developer with an interactive, visual tool that provides insights into the workings and, importantly, also into the failures of the algorithm under development. Developing visualization support for matrix calculus development went similar as the development of more traditional visual support systems for data analysts. First, we had to acquaint ourselves with the problem, its language and challenges by talking to the core developer of the matrix calculus algorithm. Once we understood the challenge, it was fairly easy to develop visual support that streamlined the development of the matrix calculus algorithm significantly.

show abstract

Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow

Cited by 270 publications

References 33 publications

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Analyzing the Noise Robustness of Deep Neural Networks

Visualization Support for Developing a Matrix Calculus Algorithm: A Case Study

Contact Info

Product

Resources

About