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 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 (1)
Tasks
Common Sense ReasoningSegmentationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
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…
Common Sense ReasoningSegmentationtext-classificationText ClassificationMartingale Posterior Neural Processes
A Neural Process (NP) estimates a stochastic process implicitly defined with neural networks given a stream of data, rather than pre-specifying priors already known, such as Gaussian processes. An ideal NP would learn ev…
Bayesian InferenceGaussian ProcessesGenerative Posterior Networks for Approximately Bayesian Epistemic Uncertainty Estimation
In many real-world problems, there is a limited set of training data, but an abundance of unlabeled data. We propose a new method, Generative Posterior Networks (GPNs), that uses unlabeled data to estimate epistemic unce…
Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last laye…
Computational EfficiencyOut-of-Distribution DetectionUncertainty QuantificationThompson Sampling via Local Uncertainty
Thompson sampling is an efficient algorithm for sequential decision making, which exploits the posterior uncertainty to address the exploration-exploitation dilemma. There has been significant recent interest in integrat…
Decision MakingMulti-Armed BanditsSequential Decision MakingThompson Sampling+1