Kernelized Concept Erasure

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ravfogel, Shauli, Vargas, Francisco, Goldberg, Yoav, Cotterell, Ryan
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916394858184704
author Ravfogel, Shauli
Vargas, Francisco
Goldberg, Yoav
Cotterell, Ryan
author_facet Ravfogel, Shauli
Vargas, Francisco
Goldberg, Yoav
Cotterell, Ryan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2201_12191
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Kernelized Concept Erasure
Ravfogel, Shauli
Vargas, Francisco
Goldberg, Yoav
Cotterell, Ryan
Machine Learning
Computation and Language
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.
title Kernelized Concept Erasure
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2201.12191