Robust Learning from Discriminative Feature Feedback
Recent work introduced the model of learning from discriminative feature feedback, in which a human annotator not only provides labels of instances, but also identifies discriminative features that highlight important differences between pairs of instances. It was shown that such feedback can be conducive to learning, and makes it possible to efficiently learn some concept classes that would otherwise be intractable. However, these results all relied upon perfect annotator feedback. In this paper, we introduce a more realistic, robust version of the framework, in which the annotator is allowed to make mistakes. We show how such errors can be handled algorithmically, in both an adversarial and a stochastic setting. In particular, we derive regret bounds in both settings that, as in the case of a perfect annotator, are independent of the number of features. We show that this result cannot be obtained by a naive reduction from the robust setting to the non-robust setting.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize the novel object categories using the semantic representation of categories, and the key idea is to explore the knowledge of how the novel class is semantically related to the f…
DecoderGeneralized Zero-Shot LearningObject RecognitionZero-Shot LearningDiscriminative Feature Feedback with General Teacher Classes
We study the theoretical properties of the interactive learning protocol Discriminative Feature Feedback (DFF) (Dasgupta et al., 2018). The DFF learning protocol uses feedback in the form of discriminative feature explan…
Improved Robust Algorithms for Learning with Discriminative Feature Feedback
Discriminative Feature Feedback is a setting proposed by Dastupta et al. (2018), which provides a protocol for interactive learning based on feature explanations that are provided by a human teacher. The features disting…
Learning from discriminative feature feedback
We consider the problem of learning a multi-class classifier from labels as well as simple explanations that we call "discriminative features". We show that such explanations can be provided whenever the target concept i…
Do text-free diffusion models learn discriminative visual representations?
While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks si…
image-classificationImage Classificationobject-detectionObject Detection+2