.png){kind=icon}
.png){kind=icon}
Return
Label distribution learning via implicit distribution representation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.133029.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In contrast to multi-label learning, label distribution learning characterizes the polysemy of examples by a label distribution to represent richer semantics. In the learning process of label distribution, the training data is collected mainly through manual annotation or label enhancement algorithms to generate label distribution. Unfortunately, the complexity of the manual annotation task or the inaccuracy of the label enhancement algorithm leads to noise and uncertainty in the label distribution training set. To alleviate this problem, we introduce the implicit distribution in the label distribution learning framework to characterize the uncertainty of each label value. Specifically, we use deep implicit representation learning to construct a label distribution matrix with Gaussian prior constraints, where each row component corresponds to the distribution estimate of each label value, and this row component is constrained by a prior Gaussian distribution to moderate the noise and uncertainty interference in the label distribution dataset. Finally, each row component of the label distribution matrix is transformed into a standard label distribution form by using the self-attention algorithm. We evaluate our model using several representative metrics, such as Chebyshev distance (0.0779 ± 0.0021) and KL divergence (0.0404 ± 0.0020), and demonstrate that our method achieves significant improvements in performance, mitigating noise and enhancing label distribution accuracy. The code is publicly available at: https://github.com/WaterHQH/SNNGCN .
Keywords:
label distribution learning
implicit distribution
Gaussian prior
self-attention
noise mitigation
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
View more organizations