paper-with-me

홈 › Papers

Controllable Invariance through Adversarial Feature Learning

2017-05-31 · NeurIPS 2017 12 · Qizhe Xie, Zihang Dai, Yulun Du, Eduard Hovy, Graham Neubig

Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning representations invariant to a specific factor or trait of data. The representation learning process is formulated as an adversarial minimax game. We analyze the optimal equilibrium of such a game and find that it amounts to maximizing the uncertainty of inferring the detrimental factor given the representation while maximizing the certainty of making task-specific predictions. On three benchmark tasks, namely fair and bias-free classification, language-independent generation, and lighting-independent image classification, we show that the proposed framework induces an invariant representation, and leads to better generalization evidenced by the improved performance.

📄 PDF Abstract BibTeX arXiv:1705.11122

Code (0)

등록된 구현이 없습니다.

Tasks

General Classificationimage-classificationImage ClassificationRepresentation Learning

Similar Papers 제목 키워드 기반

Invariant Representations without Adversarial Training

2018-05-24 · NeurIPS 2018 12 · Daniel Moyer, Shuyang Gao, Rob Brekelmans, Greg Ver Steeg 외

Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangli…

Representation Learning

Invariant Representations through Adversarial Forgetting

2019-11-11 · Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg, Wael Abd-Almageed 외

We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechani…

Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization

2019-04-29 · Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

Learning domain-invariant representation is a dominant approach for domain generalization (DG), where we need to build a classifier that is robust toward domain shifts. However, previous domain-invariance-based methods o…

Domain Generalization

Symmetry Defense Against XGBoost Adversarial Perturbation Attacks

2023-08-10 · Blerta Lindqvist

We examine whether symmetry can be used to defend tree-based ensemble classifiers such as gradient-boosting decision trees (GBDTs) against adversarial perturbation attacks. The idea is based on a recent symmetry defense …

Domain Generalization via Entropy Regularization

2020-12-01 · NeurIPS 2020 12 · Shanshan Zhao, Mingming Gong, Tongliang Liu, Huan Fu 외

Domain generalization aims to learn from multiple source domains a predictive model that can generalize to unseen target domains. One essential problem in domain generalization is to learn discriminative domain-invariant…

Domain Generalization