Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery

• URL: http://arxiv.org/abs/2602.02726v1
• Date: Mon, 02 Feb 2026 19:43:20 GMT
• Title: Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
• Authors: Xuemin Yu, Ankur Garg, Samira Ebrahimi Kahou, Hassan Sajjad,
• Abstract summary: We propose the vector quantized latent concept (VQLC) method, a framework built upon the vector quantized-variational autoencoder (VQ-VAE) architecture.<n>We show that VQLC improves scalability while maintaining comparable quality of human-understandable explanations.
• Score: 10.6686798314267
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Learning models encode rich semantic information in their hidden representations. However, it remains challenging to understand which parts of this information models actually rely on when making predictions. A promising line of post-hoc concept-based explanation methods relies on clustering token representations. However, commonly used approaches such as hierarchical clustering are computationally infeasible for large-scale datasets, and K-Means often yields shallow or frequency-dominated clusters. We propose the vector quantized latent concept (VQLC) method, a framework built upon the vector quantized-variational autoencoder (VQ-VAE) architecture that learns a discrete codebook mapping continuous representations to concept vectors. We perform thorough evaluations and show that VQLC improves scalability while maintaining comparable quality of human-understandable explanations.

Related papers

• VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction [83.50898344094153]
  VQRAE produces Continuous semantic features for image understanding and tokens for visual generation within a unified tokenizer.<n>Design enables negligible semantic information for maintaining the ability of multimodal understanding, discrete tokens.<n>VQRAE presents competitive performance on several benchmarks of visual understanding, generation and reconstruction.
  arXiv  Detail & Related papers  (2025-11-28T17:26:34Z)
• Cross-Layer Discrete Concept Discovery for Interpreting Language Models [13.842670153893977]
  Cross-layer VQ-VAE is a framework that uses vector quantization to map representations across layers.<n>Our approach uniquely combines top-k temperature-based sampling during quantization with EMA codebook updates.
  arXiv  Detail & Related papers  (2025-06-24T22:43:36Z)
• Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery [52.498055901649025]
  Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks. We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
  arXiv  Detail & Related papers  (2024-07-19T17:50:11Z)
• MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes [24.28807025839685]
  We argue that explanations lacking insights into the decision processes of low and mid-level features are neither fully faithful nor useful. We propose a novel paradigm that learns and aligns multi-level concept prototype distributions for classification purposes via Class-aware Concept Distribution (CCD) loss.
  arXiv  Detail & Related papers  (2024-04-13T11:13:56Z)
• Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning [86.15009879251386]
  We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBM) CBMs require an additional set of concepts to leverage. We show a significant increase in accuracy using sparse hidden layers in CLIP-based bottleneck models.
  arXiv  Detail & Related papers  (2024-04-04T09:43:43Z)
• Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces [1.0923877073891446]
  Insights into the learned latent representations are imperative for verifying deep neural networks (DNNs) in computer vision tasks.<n>We propose a novel local concept analysis framework to allow exploration of learned concept distributions.<n>Despite its context sensitivity, our method's concept segmentation performance is competitive to global baselines.
  arXiv  Detail & Related papers  (2023-11-24T12:22:00Z)
• Vector Quantized Wasserstein Auto-Encoder [57.29764749855623]
  We study learning deep discrete representations from the generative viewpoint. We endow discrete distributions over sequences of codewords and learn a deterministic decoder that transports the distribution over the sequences of codewords to the data distribution. We develop further theories to connect it with the clustering viewpoint of WS distance, allowing us to have a better and more controllable clustering solution.
  arXiv  Detail & Related papers  (2023-02-12T13:51:36Z)
• Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing [97.70862116338554]
  We investigate the problem of measuring interpretability of self-supervised representations. We formulate the latter as estimating the mutual information between the representation and a space of manually labelled concepts. We use our method to evaluate a large number of self-supervised representations, ranking them by interpretability.
  arXiv  Detail & Related papers  (2022-09-07T16:18:50Z)
• Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization [76.68866368409216]
  We propose learning to dynamically select discretization tightness conditioned on inputs. We show that dynamically varying tightness in communication bottlenecks can improve model performance on visual reasoning and reinforcement learning tasks.
  arXiv  Detail & Related papers  (2022-02-02T23:54:26Z)
• Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors [24.581839689833572]
  Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. Recent work on explanations through feature importance of approximate linear models has moved from input-level features to features from mid-layer feature maps in the form of concept activation vectors (CAVs) In this work, we rethink the ACE algorithm of Ghorbani etal., proposing an alternative invertible concept-based explanation (ICE) framework to overcome its shortcomings.
  arXiv  Detail & Related papers  (2020-06-27T17:57:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.