Resolving label uncertainty with implicit generative models
In prediction problems, coarse and imprecise sources of input can provide rich information about labels, but are not readily used by discriminative learners. In this work, we propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label. By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs. This formulation unifies various machine learning settings: the weak beliefs can come in the form of noisy or incomplete labels, likelihoods given by a different prediction mechanism on auxiliary input, or common-sense priors reflecting knowledge about the structure of the problem at hand. We demonstrate the proposed algorithms on diverse problems: classification with negative training examples, learning from rankings, weakly and self-supervised aerial imagery segmentation, co-segmentation of video frames, and coarsely supervised text classification.
Code (0)
등록된 구현이 없습니다.
Tasks
Common Sense ReasoningSegmentationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Resolving label uncertainty with implicit posterior models
We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label. By implicitly assuming the existence of a generative …
Common Sense ReasoningSegmentationtext-classificationText ClassificationResolving Implicit References in Instructional Texts
The usage of (co-)referring expressions in discourse contributes to the coherence of a text. However, text comprehension can be difficult when referring expressions are non-verbalized and have to be resolved in the disco…
Reading ComprehensionPartial Label Supervision for Agnostic Generative Noisy Label Learning
Noisy label learning has been tackled with both discriminative and generative approaches. Despite the simplicity and efficiency of discriminative methods, generative models offer a more principled way of disentangling cl…
Image GenerationLearning with noisy labelsPartial Label LearningCausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
We propose an adversarial training procedure for learning a causal implicit generative model for a given causal graph. We show that adversarial training can be used to learn a generative model with true observational and…
Face GenerationRandom Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields
Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predictions and shifted towa…
Gaussian Processes