mlsanityData to 14 Oct 2026

Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks

arXiv 2212.10774 ↗First posted 21 Dec 2022cs.HC cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators. Existing toolkits for visualizing computational graphs are not applicable when the structure is highly complicated and large-scale (e.g., BERT [1]). To address this problem, we propose leveraging a suite of visual simplification techniques, including a cycle-removing method, a module-based edge-pruning algorithm, and an isomorphic subgraph stacking strategy. We design and implement an interactive visualization system that is suitable for computational graphs with up to 10 thousand elements. Experimental results and usage scenarios demonstrate that our tool reduces 60% elements on average and hence enhances the performance for recognizing and diagnosing DNN models. Our contributions are integrated into an open-source DNN visualization toolkit, namely, MindInsight [2].

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 72 references that are in the map. First posted on arXiv 21 Dec 2022.

Builds on

19 of 72 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  8. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  9. 2018Techniques for Interpretable Machine Learningcited by 238
  10. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 206
  11. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  12. 2019FairSight: Visual Analytics for Fairness in Decision Makingcited by 59
7 more
  1. 2017ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Modelscited by 56
  2. 2020A Survey of Visual Analytics Techniques for Machine Learningcited by 56
  3. 2016Towards Better Analysis of Deep Convolutional Neural Networkscited by 51
  4. 2017Understanding Hidden Memories of Recurrent Neural Networkscited by 44
  5. 2017Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspectivecited by 36
  6. 2018Towards Explanation of DNN-based Prediction with Guided Feature Inversioncited by 31
  7. 2021Computational Graph Completioncited by 28

Built on by

Not cited yet.