mlsanityData to 14 Oct 2026

Improving Compositionality of Neural Networks by Decoding Representations to Inputs

arXiv 2106.00769 ↗First posted 1 Jun 2021cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated strong performance on novel applications, they sacrifice many of the functionalities of traditional software programs. With this as motivation, we take a modest first step towards improving deep learning programs by jointly training a generative model to constrain neural network activations to "decode" back to inputs. We call this design a Decodable Neural Network, or DecNN. Doing so enables a form of compositionality in neural networks, where one can recursively compose DecNN with itself to create an ensemble-like model with uncertainty. In our experiments, we demonstrate applications of this uncertainty to out-of-distribution detection, adversarial example detection, and calibration -- while matching standard neural networks in accuracy. We further explore this compositionality by combining DecNN with pretrained models, where we show promising results that neural networks can be regularized from using protected features.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 72 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

45 of 72 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  9. 2017On Calibration of Modern Neural Networkscited by 4,960
  10. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  11. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  12. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
33 more
  1. 2013Auto-Encoding Variational Bayescited by 4,053
  2. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  4. 2016Density estimation using Real NVPcited by 2,042
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  8. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  10. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  12. 2017Selective Classification for Deep Neural Networkscited by 852
  13. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  14. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  15. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  16. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  17. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  18. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  19. 2015Adversarial Autoencoderscited by 364
  20. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
  21. 2017Detecting Adversarial Samples from Artifactscited by 245
  22. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  23. 2017On Detecting Adversarial Perturbationscited by 232
  24. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 193
  25. 2020Compositional Explanations of Neuronscited by 172
  26. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 138
  27. 2016Invertible Conditional GANs for image editingcited by 118
  28. 2018Learning Controllable Fair Representationscited by 83
  29. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  30. 2020A Framework For Contrastive Self-Supervised Learning And Designing A New Approachcited by 52
  31. 2020Viewmaker Networks: Learning Views for Unsupervised Representation Learningcited by 48
  32. 2019Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matricescited by 32
  33. 2019Deep Neural Network Ensemblescited by 10

Built on by

Cited by year

Citing papers per year: 2022: 2.

2 papers.

  1. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  2. 2022Constraining Representations Yields Models That Know What They Don't Knowcited by 0