Related papers: Unsupervised Adversarial Invariance
Adversarial learning is a widely used technique in fair representation learning to remove the biases on sensitive attributes from data representations. It usually requires to incorporate the sensitive attribute labels as prediction targets.…
Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can drastically impair the network's performance. Many defense methods have been proposed for improving…
Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…
Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…
Deep neural network models for speech recognition have achieved great success recently, but they can learn incorrect associations between the target and nuisance factors of speech (e.g., speaker identities, background noise, etc.), which…
Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We…
The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…
Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…
Representational learning forms the backbone of most deep learning applications, and the value of a learned representation is intimately tied to its information content regarding different factors of variation. Finding good representations…
We investigate the power of censoring techniques, first developed for learning {\em fair representations}, to address domain generalization. We examine {\em adversarial} censoring techniques for learning invariant representations from…
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…
Fairness is becoming a rising concern w.r.t. machine learning model performance. Especially for sensitive fields such as criminal justice and loan decision, eliminating the prediction discrimination towards a certain group of population…
In this paper, we consider batch supervised learning where an adversary is allowed to corrupt instances with arbitrarily large noise. The adversary is allowed to corrupt any $l$ features in each instance and the adversary can change their…
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…
Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled…
The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we…
Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…
In this paper we present a world model, which learns causal features using the invariance principle. In particular, we use contrastive unsupervised learning to learn the invariant causal features, which enforces invariance across…
The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…