We lifted 6 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| limaosen0/GXN | canonical | 4 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| gnn_spmm | Ran | limaosen0/GXN/lib/pytorch_util.py code served (permissive licence) · get_code("60fc5a60fd9bb303") |
| normalize_adj_torch | Ran | limaosen0/GXN/ops.py code served (permissive licence) · get_code("88e5b6e8be02c080") |
| spac_normalize_adj | Ran | limaosen0/GXN/ops.py code served (permissive licence) · get_code("89fadad46806a981") |
| spec_normalize_adj | Ran | limaosen0/GXN/ops.py code served (permissive licence) · get_code("3bc0a3d3beb677d3") |
| load_data | Not yet run | limaosen0/GXN/util.py code served (permissive licence) · get_code("6729383cf19d8eb8") |
| sep_data | Not yet run | limaosen0/GXN/util.py code served (permissive licence) · get_code("7bf59fdeb79e2999") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph. Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow. Two key ingredients of GXN include a novel vertex infomax pooling (VIPool), which creates multiscale graphs in a trainable manner, and a novel feature-crossing layer, enabling feature interchange across scales. The proposed VIPool selects the most informative subset of vertices based on the neural estimation of mutual information between vertex features and neighborhood features. The intuition behind is that a vertex is informative when it can maximally reflect its neighboring information. The proposed feature-crossing layer fuses intermediate features between two scales for mutual enhancement by improving information flow and enriching multiscale features at hidden layers. The cross shape of the feature-crossing layer distinguishes GXN from many other multiscale architectures. Experimental results show that the proposed GXN improves the classification accuracy by 2.12% and 1.15% on average for graph classification and vertex classification, respectively. Based on the same network, the proposed VIPool consistently outperforms other graph-pooling methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.01804")
get_code_for_paper("2010.01804")
have("2010.01804")
Connect an agent — have() is free.