Sungsoo Ahn, Seul Lee, Yunhui Jang
We lifted 6 functions out of this paper's own repositories and ran 3 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 |
|---|---|---|
| yunhuijang/geel | canonical | 3 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| compute_sequence_accuracy | Ran | yunhuijang/geel/evaluation/evaluation.py pointer only (licence: NONE) · get_code("9891c9b08012e1bb") |
| is_planar_graph | Ran | yunhuijang/geel/evaluation/evaluation_spectre.py pointer only (licence: NONE) · get_code("c41da2d5bcbf1ce5") |
| save_graph_list | Ran | yunhuijang/geel/evaluation/evaluation.py pointer only (licence: NONE) · get_code("c57d1935c17f218b") |
| is_grid_graph | Not yet run | yunhuijang/geel/evaluation/evaluation_spectre.py pointer only (licence: NONE) · get_code("aa578bd01b587194") |
| is_sbm_graph | Not yet run | yunhuijang/geel/evaluation/evaluation_spectre.py pointer only (licence: NONE) · get_code("911626e18cbcb30c") |
| save_graph_list | Not yet run | yunhuijang/geel/plot.py pointer only (licence: NONE) · get_code("162bab265e19be94") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recently, there has been a surge of interest in employing neural networks for graph generation, a fundamental statistical learning problem with critical applications like molecule design and community analysis. However, most approaches encounter significant limitations when generating large-scale graphs. This is due to their requirement to output the full adjacency matrices whose size grows quadratically with the number of nodes. In response to this challenge, we introduce a new, simple, and scalable graph representation named gap encoded edge list (GEEL) that has a small representation size that aligns with the number of edges. In addition, GEEL significantly reduces the vocabulary size by incorporating the gap encoding and bandwidth restriction schemes. GEEL can be autoregressively generated with the incorporation of node positional encoding, and we further extend GEEL to deal with attributed graphs by designing a new grammar. Our findings reveal that the adoption of this compact representation not only enhances scalability but also bolsters performance by simplifying the graph generation process. We conduct a comprehensive evaluation across ten non-attributed and two molecular graph generation tasks, demonstrating the effectiveness of GEEL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2312.02230")
get_code_for_paper("2312.02230")
have("2312.02230")
Connect an agent — have() is free.