mlsanityData to 13 Oct 2026

Structural Causality-based Generalizable Concept Discovery Models

arXiv 2410.15491 ↗First posted 20 Oct 2024cs.LG stat.MEcited by 0

Not on the map. Why?

Abstract (arXiv)

The rising need for explainable deep neural network architectures has utilized semantic concepts as explainable units. Several approaches utilizing disentangled representation learning estimate the generative factors and utilize them as concepts for explaining DNNs. However, even though the generative factors for a dataset remain fixed, concepts are not fixed entities and vary based on downstream tasks. In this paper, we propose a disentanglement mechanism utilizing a variational autoencoder (VAE) for learning mutually independent generative factors for a given dataset and subsequently learning task-specific concepts using a structural causal model (SCM). Our method assumes generative factors and concepts to form a bipartite graph, with directed causal edges from generative factors to concepts. Experiments are conducted on datasets with known generative factors: D-sprites and Shapes3D. On specific downstream tasks, our proposed method successfully learns task-specific concepts which are explained well by the causal edges from the generative factors. Lastly, separate from current causal concept discovery methods, our methodology is generalizable to an arbitrary number of concepts and flexible to any downstream tasks.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 18 of its 33 references that are in the map. First posted on arXiv 20 Oct 2024.

Builds on

18 of 33 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,316
  4. 2020Concept Bottleneck Modelscited by 1,027
  5. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 934
  6. 2016Ladder Variational Autoencoderscited by 318
  7. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  8. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  9. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  10. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  11. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  12. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
6 more
  1. 2020Weakly Supervised Disentangled Generative Causal Representation Learningcited by 68
  2. 2013Equitability, mutual information, and the maximal information coefficientcited by 45
  3. 2020Generative causal explanations of black-box classifierscited by 41
  4. 2022Understanding and Enhancing Robustness of Concept-based Modelscited by 22
  5. 2020Causal Adversarial Network for Learning Conditional and Interventional Distributionscited by 13
  6. 2022Provable concept learning for interpretable predictions using variational autoencoderscited by 9

Built on by

Not cited yet.