mlsanityData to 7 Oct 2026

EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors

arXiv 2409.14630 ↗First posted 22 Sep 2024cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable concepts to enhance interpretability. However, existing CBMs face challenges due to deterministic concept encoding and reliance on inconsistent concepts, leading to inaccuracies. We propose EQ-CBM, a novel framework that enhances CBMs through probabilistic concept encoding using energy-based models (EBMs) with quantized concept activation vectors (qCAVs). EQ-CBM effectively captures uncertainties, thereby improving prediction reliability and accuracy. By employing qCAVs, our method selects homogeneous vectors during concept encoding, enabling more decisive task performance and facilitating higher levels of human intervention. Empirical results using benchmark datasets demonstrate that our approach outperforms the state-of-the-art in both concept and task accuracy.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 28 of its 44 references that are in the map. First posted on arXiv 22 Sep 2024.

Builds on

28 of 44 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017Neural Discrete Representation Learningcited by 4,650
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  9. 2020Concept Bottleneck Modelscited by 1,022
  10. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  11. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  12. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
16 more
  1. 2022Post-hoc Concept Bottleneck Modelscited by 289
  2. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
  3. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 147
  4. 2016Energy-based Generative Adversarial Networkcited by 119
  5. 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
  6. 2020Learning Latent Space Energy-Based Prior Modelcited by 104
  7. 2023Probabilistic Concept Bottleneck Modelscited by 101
  8. 2022Interactive Concept Bottleneck Modelscited by 79
  9. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  10. 2021A Framework for Learning Ante-hoc Explainable Models via Conceptscited by 45
  11. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
  12. 2017Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Samplingcited by 32
  13. 2020Joint Training of Variational Auto-Encoder and Latent Energy-Based Modelcited by 30
  14. 2021JEM++: Improved Techniques for Training JEMcited by 28
  15. 2023EGC: Image Generation and Classification via a Diffusion Energy-Based Modelcited by 16
  16. 2022Energy-Based Contrastive Learning of Visual Representationscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Representation Engineering for Large-Language Models: Survey and Research Challengescited by 18
  2. 2025Leakage and Interpretability in Concept-Based Modelscited by 13
  3. 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimizationcited by 7
  4. 2025Parameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck Modelscited by 1
  5. 2025CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapescited by 0
  6. 2026Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Modelscited by 0