Probabilistic Decoupling of Labels in Classification
In this paper we develop a principled, probabilistic, unified approach to non-standard classification tasks, such as semi-supervised, positive-unlabelled, multi-positive-unlabelled and noisy-label learning. We train a classifier on the given labels to predict the label-distribution. We then infer the underlying class-distributions by variationally optimizing a model of label-class transitions.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Probabilistic Decoupling of Labels in Classification
We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, includ…
ClassificationGeneral ClassificationTackling Multilabel Imbalance through Label Decoupling and Data Resampling Hybridization
The learning from imbalanced data is a deeply studied problem in standard classification and, in recent times, also in multilabel classification. A handful of multilabel resampling methods have been proposed in late year…
General ClassificationGraph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification
Graph neural networks (GNN) have been ubiquitous in graph node classification tasks. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' information. However, they often suffer from ne…
General ClassificationGraph LearningHard AttentionNode ClassificationLearning from Similarity/Dissimilarity and Pairwise Comparison
This paper addresses binary classification in scenarios where obtaining explicit instance level labels is impractical, by exploiting multiple weak labels defined on instance pairs. The existing SconfConfDiff classificati…
Binary ClassificationFeature Decoupling in Self-supervised Representation Learning for Open Set Recognition
Assuming unknown classes could be present during classification, the open set recognition (OSR) task aims to classify an instance into a known class or reject it as unknown. In this paper, we use a two-stage training str…
Open Set LearningRepresentation Learning