Abstract | ||
---|---|---|
Graph convolutional networks (GCNs) are a widely used method for graph representation learning. To elucidate their capabilities and limitations for graph classification, we investigate their power to generate well-separated embedding vectors for graphs sampled from different random graph models, which correspond to different class-conditional distributions in a classification problem. It has been ... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TIT.2022.3145847 | IEEE Transactions on Information Theory |
Keywords | DocType | Volume |
Measurement,Representation learning,Task analysis,Convolution,Upper bound,Testing,Signal processing algorithms | Journal | 68 |
Issue | ISSN | Citations |
5 | 0018-9448 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Abram Magner | 1 | 3 | 7.24 |
Mayank Baranwal | 2 | 8 | 6.68 |
Alfred O. Hero III | 3 | 2600 | 301.12 |