mlsanityData to 7 Oct 2026

VICE: Variational Interpretable Concept Embeddings

arXiv 2205.00756 ↗First posted 2 May 2022cs.LG stat.AP stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 19 of its 61 references that are in the map. First posted on arXiv 2 May 2022.

Builds on

19 of 61 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2016Variational Inference: A Review for Statisticianscited by 1,466
  7. 2015Weight Uncertainty in Neural Networkscited by 554
  8. 2020On the Generalization Benefit of Noise in Stochastic Gradient Descentcited by 81
  9. 2017SPINE: SParse Interpretable Neural Embeddingscited by 55
  10. 2018Posterior Concentration for Sparse Deep Learningcited by 50
  11. 2017Early Stopping without a Validation Setcited by 39
  12. 2015Early Stopping is Nonparametric Variational Inferencecited by 23
7 more
  1. 2020Enriching ImageNet with Human Similarity Judgments and Psychological Embeddingscited by 23
  2. 2019Revealing interpretable object representations from human behaviorcited by 17
  3. 2020Spike and slab variational Bayes for high dimensional logistic regressioncited by 16
  4. 2018Using Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledgecited by 5
  5. 2019Feature2Vec: Distributional semantic modelling of human property knowledgecited by 4
  6. 2018Comparing Spike and Slab Priors for Bayesian Variable Selectioncited by 2
  7. 2013Scaling the Indian Buffet Process via Submodular Maximizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

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

15 papers.

Sort:

By area:

  1. 2023Getting aligned on representational alignmentcited by 142
  2. 2022Human alignment of neural network representationscited by 74
  3. 2023Improving neural network representations using human similarity judgmentscited by 38
  4. 2024Dimensions underlying the representational alignment of deep neural networks with humanscited by 22
  5. 2022When are Post-hoc Conceptual Explanations Identifiable?cited by 14
  6. 2023Preemptively Pruning Clever-Hans Strategies in Deep Neural Networkscited by 9
  7. 2024An Analysis of Human Alignment of Latent Diffusion Modelscited by 5
  8. 2024CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representationscited by 5
  9. 2023Set Learning for Accurate and Calibrated Modelscited by 2
  10. 2025Evaluating Steering Techniques using Human Similarity Judgmentscited by 2
  11. 2024Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networkscited by 1
  12. 2025Uncovering the Computational Ingredients of Human-Like Representations in LLMscited by 1
3 more
  1. 2026Context Sensitivity Improves Human-Machine Visual Alignmentcited by 1
  2. 2025Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering Human Perceptual Variability on Facial Expressionscited by 0
  3. 2025Dimensions of Vulnerability in Visual Working Memory: An AI-Driven Approach to Perceptual Comparisoncited by 0