Loading...
Please wait, while we are loading the content...
Similar Documents
L G ] 1 2 M ar 2 01 8 Probabilistic and Regularized Graph Convolutional Networks ( L 42 Michaelmas 2017 )
| Content Provider | Semantic Scholar |
|---|---|
| Author | Billings, Sean |
| Copyright Year | 2018 |
| Abstract | This paper explores the recently proposed Graph Convolutional Network architecture proposed in (Kipf & Welling, 2016) The key points of their work is summarized and their results are reproduced. Graph regularization and alternative graph convolution approaches are explored. I find that explicit graph regularization was correctly rejected by (Kipf & Welling, 2016). I attempt to improve the performance of GCN by approximating a k-step transition matrix in place of the normalized graph laplacian, but I fail to find positive results. Nonetheless, the performance of several configurations of this GCN variation is shown for the Cora, Citeseer, and Pubmed datasets. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://export.arxiv.org/pdf/1803.04489 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
