mlsanityData to 7 Oct 2026

Deep Concept Removal

arXiv 2310.05755 ↗First posted 9 Oct 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We address the problem of concept removal in deep neural networks, aiming to learn representations that do not encode certain specified concepts (e.g., gender etc.) We propose a novel method based on adversarial linear classifiers trained on a concept dataset, which helps to remove the targeted attribute while maintaining model performance. Our approach Deep Concept Removal incorporates adversarial probing classifiers at various layers of the network, effectively addressing concept entanglement and improving out-of-distribution generalization. We also introduce an implicit gradient-based technique to tackle the challenges associated with adversarial training using linear classifiers. We evaluate the ability to remove a concept on a set of popular distributionally robust optimization (DRO) benchmarks with spurious correlations, as well as out-of-distribution (OOD) generalization tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 9 Oct 2023.

Builds on

27 of 33 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  5. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  8. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  9. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  10. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  11. 2018Recognition in Terra Incognitacited by 655
  12. 2019Meta-Learning with Implicit Gradientscited by 523
15 more
  1. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  2. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  3. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  4. 2019Optimizing Millions of Hyperparameters by Implicit Differentiationcited by 303
  5. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  6. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  7. 2015The Variational Fair Autoencodercited by 223
  8. 2020Coresets via Bilevel Optimization for Continual Learning and Streamingcited by 191
  9. 2021Simple data balancing achieves competitive worst-group-accuracycited by 177
  10. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 166
  11. 2018Invariant Representations without Adversarial Trainingcited by 111
  12. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  13. 2022Concept Activation Regions: A Generalized Framework For Concept-Based Explanationscited by 57
  14. 2020An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognitioncited by 30
  15. 2019Learning Fair Representations via an Adversarial Frameworkcited by 29

Built on by

Not cited yet.