paper-with-me

Papers

Graph-Based Posterior Regularization for Semi-Supervised Structured Prediction

2013-08-01 · WS 2013 8 · Luheng He, Jennifer Gillenwater, Ben Taskar
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Structured Prediction

Similar Papers 제목 키워드 기반

A Flexible Generative Framework for Graph-based Semi-supervised Learning

2019-05-26 · NeurIPS 2019 12 · Jiaqi Ma, Weijing Tang, Ji Zhu, Qiaozhu Mei

We consider a family of problems that are concerned about making predictions for the majority of unlabeled, graph-structured data samples based on a small proportion of labeled samples. Relational information among the d…

Missing LabelsVariational Inference

Bethe Projections for Non-Local Inference

2015-03-04 · Luke Vilnis, David Belanger, Daniel Sheldon, Andrew McCallum

Many inference problems in structured prediction are naturally solved by augmenting a tractable dependency structure with complex, non-local auxiliary objectives. This includes the mean field family of variational infere…

Handwriting RecognitionStructured PredictionVariational Inference

Posterior Differential Regularization with f-divergence for Improving Model Robustness

2020-10-23 · NAACL 2021 4 · Hao Cheng, Xiaodong Liu, Lis Pereira, YaoLiang Yu 외

We address the problem of enhancing model robustness through regularization. Specifically, we focus on methods that regularize the model posterior difference between clean and noisy inputs. Theoretically, we provide a co…

Domain Generalization

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

2020-05-07 · Ines Chami, Sami Abu-El-Haija, Bryan Perozzi, Christopher Ré 외

There has been a surge of recent interest in learning representations for graph-structured data. Graph representation learning methods have generally fallen into three main categories, based on the availability of labele…

BIG-bench Machine LearningDecoderGraph AttentionGraph Embedding+3

Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance

2018-05-26 · NeurIPS 2018 12 · Neal Jean, Sang Michael Xie, Stefano Ermon

Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep ke…

Gaussian ProcessesregressionRepresentation Learning