We lifted 6 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| thisisforreview/svd-gcn | canonical | 5 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| get_SVD_operator | Ran | thisisforreview/svd-gcn/FrameletSVD_GCN.py pointer only (licence: GPL-3.0) · get_code("99aedb34d18c4336") |
| multiScales | Ran | thisisforreview/svd-gcn/FrameletSVD_GCN.py pointer only (licence: GPL-3.0) · get_code("56cc5219c66d74d0") |
| nodeAttack | Ran | thisisforreview/svd-gcn/FrameletSVD_Cheby_GCN_Sparse.py pointer only (licence: GPL-3.0) · get_code("ae94e180f9762992") |
| scipy_to_torch_sparse | Ran | thisisforreview/svd-gcn/FrameletSVD_Cheby_GCN_Sparse.py pointer only (licence: GPL-3.0) · get_code("fabea7d30c29764b") |
| waveletShrinkage | Ran | thisisforreview/svd-gcn/FrameletSVD_GCN.py pointer only (licence: GPL-3.0) · get_code("8b455080a25f365c") |
| ChebyshevApprox | Not yet run | thisisforreview/svd-gcn/FrameletSVD_Cheby_GCN_Sparse.py pointer only (licence: GPL-3.0) · get_code("34b82f5922857186") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this paper, we propose a simple yet effective graph neural network for directed graphs (digraph) based on the classic Singular Value Decomposition (SVD), named SVD-GCN. The new graph neural network is built upon the graph SVD-framelet to better decompose graph signals on the SVD ``frequency'' bands. Further the new framelet SVD-GCN is also scaled up for larger scale graphs via using Chebyshev polynomial approximation. Through empirical experiments conducted on several node classification datasets, we have found that SVD-GCN has remarkable improvements in a variety of graph node learning tasks and it outperforms GCN and many other state-of-the-art graph neural networks for digraphs. Moreover, we empirically demonstate that the SVD-GCN has great denoising capability and robustness to high level graph data attacks. The theoretical and experimental results prove that the SVD-GCN is effective on a variant of graph datasets, meanwhile maintaining stable and even better performance than the state-of-the-arts.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.09335")
get_code_for_paper("2205.09335")
have("2205.09335")
Connect an agent — have() is free.