# VICE: Variational Interpretable Concept Embeddings

arXiv: https://arxiv.org/abs/2205.00756 · HTML: https://mlsanity.com/paper/2205.00756/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 61 references that are in the map.
- First posted on arXiv 2 May 2022.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [On the Generalization Benefit of Noise in Stochastic Gradient Descent](https://mlsanity.com/paper/2006.15081/) (2020)
- [SPINE: SParse Interpretable Neural Embeddings](https://mlsanity.com/paper/1711.08792/) (2017)
- [Posterior Concentration for Sparse Deep Learning](https://mlsanity.com/paper/1803.09138/) (2018)
- [Early Stopping without a Validation Set](https://mlsanity.com/paper/1703.09580/) (2017)
- [Early Stopping is Nonparametric Variational Inference](https://mlsanity.com/paper/1504.01344/) (2015)
- [Enriching ImageNet with Human Similarity Judgments and Psychological Embeddings](https://mlsanity.com/paper/2011.11015/) (2020)
- [Revealing interpretable object representations from human behavior](https://mlsanity.com/paper/1901.02915/) (2019)
- [Spike and slab variational Bayes for high dimensional logistic regression](https://mlsanity.com/paper/2010.11665/) (2020)
- [Using Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge](https://mlsanity.com/paper/1809.02534/) (2018)
- [Feature2Vec: Distributional semantic modelling of human property knowledge](https://mlsanity.com/paper/1908.11439/) (2019)
- [Comparing Spike and Slab Priors for Bayesian Variable Selection](https://mlsanity.com/paper/1812.07259/) (2018)
- [Scaling the Indian Buffet Process via Submodular Maximization](https://mlsanity.com/paper/1304.3285/) (2013)

## Built on by (most cited first, 15 of 15)

- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Human alignment of neural network representations](https://mlsanity.com/paper/2211.01201/) (2022)
- [Improving neural network representations using human similarity judgments](https://mlsanity.com/paper/2306.04507/) (2023)
- [Dimensions underlying the representational alignment of deep neural networks with humans](https://mlsanity.com/paper/2406.19087/) (2024)
- [When are Post-hoc Conceptual Explanations Identifiable?](https://mlsanity.com/paper/2206.13872/) (2022)
- [Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks](https://mlsanity.com/paper/2304.05727/) (2023)
- [An Analysis of Human Alignment of Latent Diffusion Models](https://mlsanity.com/paper/2403.08469/) (2024)
- [CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations](https://mlsanity.com/paper/2404.16482/) (2024)
- [Set Learning for Accurate and Calibrated Models](https://mlsanity.com/paper/2307.02245/) (2023)
- [Evaluating Steering Techniques using Human Similarity Judgments](https://mlsanity.com/paper/2505.19333/) (2025)
- [Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks](https://mlsanity.com/paper/2409.06362/) (2024)
- [Uncovering the Computational Ingredients of Human-Like Representations in LLMs](https://mlsanity.com/paper/2510.01030/) (2025)
- [Context Sensitivity Improves Human-Machine Visual Alignment](https://mlsanity.com/paper/2604.13883/) (2026)
- [Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering Human Perceptual Variability on Facial Expressions](https://mlsanity.com/paper/2507.14549/) (2025)
- [Dimensions of Vulnerability in Visual Working Memory: An AI-Driven Approach to Perceptual Comparison](https://mlsanity.com/paper/2507.22067/) (2025)

## 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.