mlsanityData to 14 Oct 2026

On the Versatile Uses of Partial Distance Correlation in Deep Learning

arXiv 2207.09684 ↗First posted 20 Jul 2022cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Comparing the functional behavior of neural network models, whether it is a single network over time or two (or more networks) during or post-training, is an essential step in understanding what they are learning (and what they are not), and for identifying strategies for regularization or efficiency improvements. Despite recent progress, e.g., comparing vision transformers to CNNs, systematic comparison of function, especially across different networks, remains difficult and is often carried out layer by layer. Approaches such as canonical correlation analysis (CCA) are applicable in principle, but have been sparingly used so far. In this paper, we revisit a (less widely known) from statistics, called distance correlation (and its partial variant), designed to evaluate correlation between feature spaces of different dimensions. We describe the steps necessary to carry out its deployment for large scale models -- this opens the door to a surprising array of applications ranging from conditioning one deep model w.r.t. another, learning disentangled representations as well as optimizing diverse models that would directly be more robust to adversarial attacks. Our experiments suggest a versatile regularizer (or constraint) with many advantages, which avoids some of the common difficulties one faces in such analyses. Code is at https://github.com/zhenxingjian/Partial_Distance_Correlation.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 46 of its 75 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

46 of 75 references.

References · 46

  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. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  11. 2019Searching for MobileNetV3cited by 1,994
  12. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
34 more
  1. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  2. 2016Group Equivariant Convolutional Networkscited by 1,165
  3. 2014Certifying and removing disparate impactcited by 715
  4. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
  5. 2018Disentangling by Factorisingcited by 616
  6. 2018Do Better ImageNet Models Transfer Better?cited by 565
  7. 2020What is being transferred in transfer learning?cited by 368
  8. 2018Insights on representational similarity in neural networks with canonical correlationcited by 324
  9. 2020Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depthcited by 245
  10. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  11. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  12. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  13. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  14. 2018Invariant Representations without Adversarial Trainingcited by 112
  15. 2021Repulsive Deep Ensembles are Bayesiancited by 104
  16. 2018Learning Controllable Fair Representationscited by 83
  17. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  18. 2021Differentiable Quality Diversitycited by 72
  19. 2014DenseNet: Implementing Efficient ConvNet Descriptor Pyramidscited by 66
  20. 2019Disentangling Factors of Variation Using Few Labelscited by 57
  21. 2019What it Thinks is Important is Important: Robustness Transfers through Input Gradientscited by 34
  22. 2021An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wildcited by 30
  23. 2014Block stochastic gradient iteration for convex and nonconvex optimizationcited by 22
  24. 2020FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regretcited by 22
  25. 2021On Stein Variational Neural Network Ensemblescited by 21
  26. 2013Partial Distance Correlation with Methods for Dissimilaritiescited by 20
  27. 2021Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolutioncited by 20
  28. 2020Measuring the Biases and Effectiveness of Content-Style Disentanglementcited by 14
  29. 2017Stochastic Canonical Correlation Analysiscited by 7
  30. 2021An Online Riemannian PCA for Stochastic Canonical Correlation Analysiscited by 7
  31. 2022Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasetscited by 7
  32. 2021Learning Invariant Representations using Inverse Contrastive Losscited by 6
  33. 2019Sitatapatra: Blocking the Transfer of Adversarial Samplescited by 4
  34. 2017Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifierscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 4; 2025: 6; 2026: 2.

19 papers.

Sort:

By area:

  1. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  2. 2024Neural Lineagecited by 9
  3. 2024Disentangling representations of retinal images with generative modelscited by 8
  4. 2023Equiangular Basis Vectorscited by 7
  5. 2023Continual Learning From a Stream of APIscited by 6
  6. 2023Audio Embeddings as Teachers for Music Classificationcited by 5
  7. 2024Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representationscited by 4
  8. 2023A Distance Correlation-Based Approach to Characterize the Effectiveness of Recurrent Neural Networks for Time Series Forecastingcited by 3
  9. 2024Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imagingcited by 2
  10. 2025Structured Transformations for Stable and Interpretable Neural Computationcited by 2
  11. 2025Fair Domain Generalization: An Information-Theoretic Viewcited by 1
  12. 2022Interpreting Bias in the Neural Networks: A Peek Into Representational Similaritycited by 0
7 more
  1. 2023Understanding the Benefits of Image Augmentationscited by 0
  2. 2025Fair Sufficient Representation Learningcited by 0
  3. 2025Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learningcited by 0
  4. 2025Enhancing Knowledge Transfer in Hyperspectral Image Classification via Cross-scene Knowledge Integrationcited by 0
  5. 2025Agreement Disagreement Guided Knowledge Transfer for Cross-Scene Hyperspectral Imagingcited by 0
  6. 2026Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Studycited by 0
  7. 2026From Layers to Networks: Comparing Neural Representations via Diffusion Geometrycited by 0