mlsanityData to 14 Oct 2026

Graphs as Tools to Improve Deep Learning Methods

arXiv 2110.03999 ↗First posted 8 Oct 2021cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations. For example, DNNs require a lot of training data, which might not be available in some practical applications. In addition, when small perturbations are added to the inputs, DNNs are prone to misclassification errors. DNNs are also viewed as black-boxes and as such their decisions are often criticized for their lack of interpretability. In this chapter, we review recent works that aim at using graphs as tools to improve deep learning methods. These graphs are defined considering a specific layer in a deep learning architecture. Their vertices represent distinct samples, and their edges depend on the similarity of the corresponding intermediate representations. These graphs can then be leveraged using various methodologies, many of which built on top of graph signal processing. This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 62 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

44 of 62 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  10. 2019Simplifying Graph Convolutional Networkscited by 1,477
  11. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  12. 2016Adversarial Machine Learning at Scalecited by 936
32 more
  1. 2019Relational Knowledge Distillationcited by 889
  2. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  3. 2018Object Detection with Deep Learning: A Reviewcited by 528
  4. 2019Fantastic Generalization Measures and Where to Find Themcited by 513
  5. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  6. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  7. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  8. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 425
  9. 2018A Survey on Deep Transfer Learningcited by 419
  10. 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
  11. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  12. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  13. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  14. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  15. 2018Predicting the Generalization Gap in Deep Networks with Margin Distributionscited by 113
  16. 2019Learning Disentangled Representations for Recommendationcited by 110
  17. 2016Understanding Deep Convolutional Networkscited by 76
  18. 2013Discrete Signal Processing on Graphs: Frequency Analysiscited by 73
  19. 2017The Microsoft 2017 Conversational Speech Recognition Systemcited by 52
  20. 2020DiVA: Diverse Visual Feature Aggregation for Deep Metric Learningcited by 40
  21. 2019Graph-based Knowledge Distillation by Multi-head Attention Networkcited by 31
  22. 2017Design of graph filters and filterbankscited by 22
  23. 2019Deep geometric knowledge distillation with graphscited by 21
  24. 2018PeerNets: Exploiting Peer Wisdom Against Adversarial Attackscited by 8
  25. 2018Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustnesscited by 7
  26. 2020Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classificationcited by 7
  27. 2019Introducing Graph Smoothness Loss for Training Deep Learning Architecturescited by 6
  28. 2020Affinity Graph Supervision for Visual Recognitioncited by 4
  29. 2017MARGIN: Uncovering Deep Neural Networks using Graph Signal Analysiscited by 2
  30. 2020Predicting the Accuracy of a Few-Shot Classifiercited by 2
  31. 2019Structural Robustness for Deep Learning Architecturescited by 1
  32. 2019Improved Visual Localization via Graph Smoothingcited by 1

Built on by

Not cited yet.