Kijung Shin, Sunwoo Kim, Hyunju Kim, Dongyeong Hwang
We lifted 6 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| y0ngjaenius/cvpr2024_flowerformer | canonical | 0 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| GNNPreMP | Not yet run | y0ngjaenius/cvpr2024_flowerformer/two_cell/flowerformer_2cell.py pointer only (licence: NONE) · get_code("df948b1cb9d89d1f") |
| collate_edge_masks | Not yet run | y0ngjaenius/cvpr2024_flowerformer/utils.py pointer only (licence: NONE) · get_code("070985961091da7c") |
| collate_fn | Not yet run | y0ngjaenius/cvpr2024_flowerformer/utils.py pointer only (licence: NONE) · get_code("1466d657fc2b6567") |
| evaluation | Not yet run | y0ngjaenius/cvpr2024_flowerformer/utils.py pointer only (licence: NONE) · get_code("fa3c832aaf87cffc") |
| train_1cell | Not yet run | y0ngjaenius/cvpr2024_flowerformer/train_utils.py pointer only (licence: NONE) · get_code("1e1562902342884c") |
| train_2cell | Not yet run | y0ngjaenius/cvpr2024_flowerformer/train_utils.py pointer only (licence: NONE) · get_code("cfbe6c5308631b07") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no onesize-fits-all solution. Thus, considerable efforts have been made to quickly and accurately estimate the performances of neural architectures, without full training or evaluation, for given tasks and datasets. Neural architecture encoding has played a crucial role in the estimation, and graphbased methods, which treat an architecture as a graph, have shown prominent performance. For enhanced representation learning of neural architectures, we introduce FLOWERFORMER, a powerful graph transformer that incorporates the information flows within a neural architecture. FLOWERFORMER consists of two key components: (a) bidirectional asynchronous message passing, inspired by the flows; (b) global attention built on flow-based masking. Our extensive experiments demonstrate the superiority of FLOWERFORMER over existing neural encoding methods, and its effectiveness extends beyond computer vision models to include graph neural networks and auto speech recognition models. Our code is available at http://github .com/y0ngjaenius/CVPR2024_FLOW ERFormer.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.12821")
get_code_for_paper("2403.12821")
have("2403.12821")
Connect an agent — have() is free.