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 |
|---|---|---|
| dpstart/graphormer_new | pwc_unofficial | 4 of 5 |
| ytchx1999/Graphormer | pwc_unofficial | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| convert_to_single_emb | Ran | dpstart/graphormer_new/graphormer/wrapper.py pointer only (licence: MIT) · get_code("29264267bc4ef9cf") |
| pad_1d_unsqueeze | Ran | dpstart/graphormer_new/graphormer/collator.py pointer only (licence: MIT) · get_code("ed9c8a17fdb3d49c") |
| pad_2d_bool | Ran | dpstart/graphormer_new/graphormer/collator.py pointer only (licence: MIT) · get_code("76af4bc12f28e3b2") |
| pad_2d_unsqueeze | Ran | dpstart/graphormer_new/graphormer/collator.py pointer only (licence: MIT) · get_code("28715c03e155eec6") |
| pad_attn_bias_unsqueeze | Ran | ytchx1999/Graphormer/graphormer/collator.py pointer only (licence: MIT) · get_code("b5df9592a75e3bb9") |
| flag_bounded | Not yet run | dpstart/graphormer_new/graphormer/utils/flag.py pointer only (licence: MIT) · get_code("f08fd41391ce55ac") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our basic models. We train each model by 8-fold cross-validation, and additionally train two Graphormer models on the union of training and validation sets with different random seeds. For final submission, we use a naive ensemble for these 18 models by taking average of their outputs. Using our method, our team MachineLearning achieved 0.1200 MAE on test set, which won the first place in KDD Cup graph prediction track.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.08279")
get_code_for_paper("2106.08279")
have("2106.08279")
Connect an agent — have() is free.