|
Feature Disentanglement and Homogeneous Second Order Feature Propagation for Recommendation |
|---|---|
| รหัสดีโอไอ | |
| Creator | Yaru Zhang |
| Title | Feature Disentanglement and Homogeneous Second Order Feature Propagation for Recommendation |
| Contributor | Xijin Tang |
| Publisher | Sirindhorn International Institute of Technology, Bangkadi Campus (SIIT-BKD) |
| Publication Year | 2565 |
| Journal Title | Journal of Intelligent Informatics and Smart Technology |
| Journal Vol. | 7 |
| Page no. | 1-8 |
| Keyword | Feature disentanglement, negative effects, homogeneous neighbors |
| URL Website | https://ph05.tci-thaijo.org/index.php/JIIST |
| Website title | Journal of Intelligent Informatics and Smart Technology |
| ISSN | 2586-9167 |
| Abstract | Personalized recommendation systems mine user preference, represent item feature and thus realize recommendation by modeling user-item interaction. Because the interaction naturally forms the bipartite graph, Graph Convolution Neural Networks are used to learn representation of nodes for recommendation recently. Current approaches, however, seldom give recommendation results from causing factors. Furthermore, they may encounter over-smoothing problem when addressing dense graphs and struggle to model sparse graphs. For alleviating these problems, this paper proposes feature disentanglement and homogeneous second order feature propagation for recommendation. Features of the users and items are disentangled into two parts resulting in the final ratings. Then we improve Neighborhood Routing Algorithm via adding rating embedding so as to simultaneously learn the positive and negative effects of neighborhood nodes on the central node. Finally, we apply similar homogeneous neighbors which are statistically-validated by Bipartite Score Configuration Model to the second convolution for mitigating the problems happening on the dense graphs and sparse graphs. Experimental results on two different scale real-world datasets demonstrate the effectiveness of the proposed model. |
