Sparse Subspace Clustering for Concept Discovery (SSCCD)

• URL: http://arxiv.org/abs/2203.06043v1
• Date: Fri, 11 Mar 2022 16:15:48 GMT
• Title: Sparse Subspace Clustering for Concept Discovery (SSCCD)
• Authors: Johanna Vielhaben, Stefan Bl\"ucher, and Nils Strodthoff
• Abstract summary: Concepts are key building blocks of higher level human understanding. Local attribution methods do not allow to identify coherent model behavior across samples. We put forward a new definition of concepts as low-dimensional subspaces of hidden feature layers.
• Score: 1.7319807100654885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Concepts are key building blocks of higher level human understanding. Explainable AI (XAI) methods have shown tremendous progress in recent years, however, local attribution methods do not allow to identify coherent model behavior across samples and therefore miss this essential component. In this work, we study concept-based explanations and put forward a new definition of concepts as low-dimensional subspaces of hidden feature layers. We novelly apply sparse subspace clustering to discover these concept subspaces. Moving forward, we derive insights from concept subspaces in terms of localized input (concept) maps, show how to quantify concept relevances and lastly, evaluate similarities and transferability between concepts. We empirically demonstrate the soundness of the proposed Sparse Subspace Clustering for Concept Discovery (SSCCD) method for a variety of different image classification tasks. This approach allows for deeper insights into the actual model behavior that would remain hidden from conventional input-level heatmaps.

Related papers

• 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)
• How to Blend Concepts in Diffusion Models [48.68800153838679]
  Recent methods exploit multiple latent representations and their connection, making this research question even more entangled. Our goal is to understand how operations in the latent space affect the underlying concepts. Our conclusion is that concept blending through space manipulation is possible, although the best strategy depends on the context of the blend.
  arXiv  Detail & Related papers  (2024-07-19T13:05:57Z)
• Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision [25.449397570387802]
  We propose an unsupervised method for discovering distributed representations of concepts by selecting a principal subset of neurons. Our empirical findings demonstrate that instances with similar neuron activation states tend to share coherent concepts. It can be utilized to identify unlabeled subclasses within data and to detect the causes of misclassifications.
  arXiv  Detail & Related papers  (2023-12-28T07:33:51Z)
• Local Concept Embeddings for Analysis of Concept Distributions in DNN Feature Spaces [1.0923877073891446]
  We propose a novel concept analysis framework for deep neural networks (DNNs) Instead of optimizing a single global concept vector on the complete dataset, it generates a local concept embedding (LoCE) vector for each individual sample. Despite its context sensitivity, our method's concept segmentation performance is competitive to global baselines.
  arXiv  Detail & Related papers  (2023-11-24T12:22:00Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)
• CRAFT: Concept Recursive Activation FacTorization for Explainability [5.306341151551106]
  CRAFT is a novel approach to identify both "what" and "where" by generating concept-based explanations. We conduct both human and computer vision experiments to demonstrate the benefits of the proposed approach.
  arXiv  Detail & Related papers  (2022-11-17T14:22:47Z)
• Concept Activation Regions: A Generalized Framework For Concept-Based Explanations [95.94432031144716]
  Existing methods assume that the examples illustrating a concept are mapped in a fixed direction of the deep neural network's latent space. In this work, we propose allowing concept examples to be scattered across different clusters in the DNN's latent space. This concept activation region (CAR) formalism yields global concept-based explanations and local concept-based feature importance.
  arXiv  Detail & Related papers  (2022-09-22T17:59:03Z)
• Concept Gradient: Concept-based Interpretation Without Linear Assumption [77.96338722483226]
  Concept Activation Vector (CAV) relies on learning a linear relation between some latent representation of a given model and concepts. We proposed Concept Gradient (CG), extending concept-based interpretation beyond linear concept functions. We demonstrated CG outperforms CAV in both toy examples and real world datasets.
  arXiv  Detail & Related papers  (2022-08-31T17:06:46Z)
• Human-Centered Concept Explanations for Neural Networks [47.71169918421306]
  We introduce concept explanations including the class of Concept Activation Vectors (CAV) We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats. Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.
  arXiv  Detail & Related papers  (2022-02-25T01:27:31Z)
• Discovering Concepts in Learned Representations using Statistical Inference and Interactive Visualization [0.76146285961466]
  Concept discovery is important for bridging the gap between non-deep learning experts and model end-users. Current approaches include hand-crafting concept datasets and then converting them to latent space directions. In this study, we offer another two approaches to guide user discovery of meaningful concepts, one based on multiple hypothesis testing, and another on interactive visualization.
  arXiv  Detail & Related papers  (2022-02-09T22:29:48Z)
• MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks [10.06397994266945]
  We propose MACE: a Model Agnostic Concept Extractor, which can explain the working of a convolutional network through smaller concepts. We validate our framework using VGG16 and ResNet50 CNN architectures, and on datasets like Animals With Attributes 2 (AWA2) and Places365.
  arXiv  Detail & Related papers  (2020-11-03T04:40:49Z)

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.