CSL is a synthetic dataset introduced in Murphy et al. (2019) to test the expressivity of GNNs. In particular, graphs are isomorphic if they have the same degree and the task is to classify non-isomorphic graphs.
Variants: CSL
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Text Generation | BART (TextBox 2.0) | TextBox 2.0: A Text Generation … | 2022-12-26 |
| Graph Classification | CIN | Weisfeiler and Lehman Go Cellular: … | 2021-06-23 |
Recent papers with results on this dataset: