Timezone: »
Partial label learning (PLL) is a typical weakly supervised learning problem, where each training example is associated with a set of candidate labels among which only one is true. Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels. However, this assumption is not realistic since the candidate labels are always instancedependent. In this paper, we consider instancedependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature. The incorrect label with a high degree is more likely to be annotated as the candidate label. Therefore, the latent label distribution is the essential labeling information in partially labeled examples and worth being leveraged for predictive model training. Motivated by this consideration, we propose a novel PLL method that recovers the label distribution as a label enhancement (LE) process and trains the predictive model iteratively in every epoch. Specifically, we assume the true posterior density of the latent label distribution takes on the variational approximate Dirichlet density parameterized by an inference model. Then the evidence lower bound is deduced for optimizing the inference model and the label distributions generated from the variational posterior are utilized for training the predictive model. Experiments on benchmark and realworld datasets validate the effectiveness of the proposed method. Source code is available at https://github.com/palmml/valen.
Author Information
Ning Xu (Southeast University)
Congyu Qiao (Southeast University)
Xin Geng (Southeast University)
MinLing Zhang (Southeast University)
Related Events (a corresponding poster, oral, or spotlight)

2021 Poster: InstanceDependent Partial Label Learning »
Wed. Dec 8th 08:30  10:00 AM Room
More from the Same Authors

2022 Poster: MultiInstance Causal Representation Learning for Instance Label Prediction and OutofDistribution Generalization »
Weijia Zhang · Xuanhui Zhang · hanwen deng · MinLing Zhang 
2022 Panel: Panel 2B2: One Positive Labelâ€¦ & Calibrated DataDependent Constraintsâ€¦ »
Songkai Xue · Ning Xu 
2022 Poster: One Positive Label is Sufficient: SinglePositive MultiLabel Learning with Label Enhancement »
Ning Xu · Congyu Qiao · Jiaqi Lv · Xin Geng · MinLing Zhang 
2021 Poster: Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence »
DengBao Wang · Lei Feng · MinLing Zhang 
2020 Poster: SemiSupervised Partial Label Learning via ConfidenceRated Margin Maximization »
Wei Wang · MinLing Zhang 
2020 Poster: Provably Consistent PartialLabel Learning »
Lei Feng · Jiaqi Lv · Bo Han · Miao Xu · Gang Niu · Xin Geng · Bo An · Masashi Sugiyama