Un-normalized hypergraph p-Laplacian based semi-supervised learning methods
This addresses the problem of incomplete sample relationships in semi-supervised learning for classification tasks, offering an incremental improvement over existing hypergraph methods.
The paper tackles the limitation of pairwise relationships in network-based machine learning by proposing un-normalized hypergraph p-Laplacian semi-supervised learning methods, which incorporate group-level information; experiments on the zoo and 20 newsgroups datasets show significantly greater accuracy compared to the state-of-the-art hypergraph Laplacian method with p=2.
Most network-based machine learning methods assume that the labels of two adjacent samples in the network are likely to be the same. However, assuming the pairwise relationship between samples is not complete. The information a group of samples that shows very similar pattern and tends to have similar labels is missed. The natural way overcoming the information loss of the above assumption is to represent the feature dataset of samples as the hypergraph. Thus, in this paper, we will present the un-normalized hypergraph p-Laplacian semi-supervised learning methods. These methods will be applied to the zoo dataset and the tiny version of 20 newsgroups dataset. Experiment results show that the accuracy performance measures of these un-normalized hypergraph p-Laplacian based semi-supervised learning methods are significantly greater than the accuracy performance measure of the un-normalized hypergraph Laplacian based semi-supervised learning method (the current state of the art method hypergraph Laplacian based semi-supervised learning method for classification problem with p=2).