Related papers: Kernelized Concept Erasure

Kernelized Concept Erasure

URL: http://arxiv.org/abs/2201.12191v6
Date: Sun, 15 Sep 2024 21:37:58 GMT
Title: Kernelized Concept Erasure
Authors: Shauli Ravfogel, Francisco Vargas, Yoav Goldberg, Ryan Cotterell,
Abstract summary: We propose a kernelization of a linear minimax game for concept erasure. It is possible to prevent specific non-linear adversaries from predicting the concept. However, the protection does not transfer to different nonlinear adversaries.
Score: 108.65038124096907
License: http://creativecommons.org/licenses/by/4.0/
Abstract: The representation space of neural models for textual data emerges in an unsupervised manner during training. Understanding how those representations encode human-interpretable concepts is a fundamental problem. One prominent approach for the identification of concepts in neural representations is searching for a linear subspace whose erasure prevents the prediction of the concept from the representations. However, while many linear erasure algorithms are tractable and interpretable, neural networks do not necessarily represent concepts in a linear manner. To identify non-linearly encoded concepts, we propose a kernelization of a linear minimax game for concept erasure. We demonstrate that it is possible to prevent specific non-linear adversaries from predicting the concept. However, the protection does not transfer to different nonlinear adversaries. Therefore, exhaustively erasing a non-linearly encoded concept remains an open problem.

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)
VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability [15.864519662894034]
We visualize and quantify the predictive uncertainty of gradient-based visual explanations for neural networks. Visual post hoc explainability techniques highlight features within an image to justify a network's prediction. We show that every image, network, prediction, and explanatory technique has a unique uncertainty.
arXiv Detail & Related papers (2024-06-01T23:32:29Z)
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)
Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification [19.306487616731765]
Post-hoc analysis can only discover the patterns or rules that naturally exist in models. We proactively instill knowledge to alter the representation of human-understandable concepts in hidden layers. Our method improves model interpretability, showing better disentanglement of semantic concepts, without negatively affecting model classification performance.
arXiv Detail & Related papers (2023-07-10T04:54:05Z)
Log-linear Guardedness and its Implications [116.87322784046926]
Methods for erasing human-interpretable concepts from neural representations that assume linearity have been found to be tractable and useful. This work formally defines the notion of log-linear guardedness as the inability of an adversary to predict the concept directly from the representation. We show that, in the binary case, under certain assumptions, a downstream log-linear model cannot recover the erased concept.
arXiv Detail & Related papers (2022-10-18T17:30:02Z)
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)
Linear Adversarial Concept Erasure [108.37226654006153]
We formulate the problem of identifying and erasing a linear subspace that corresponds to a given concept. We show that the method is highly expressive, effectively mitigating bias in deep nonlinear classifiers while maintaining tractability and interpretability.
arXiv Detail & Related papers (2022-01-28T13:00:17Z)

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