Wenwu Zhu, Xu Chu, Xinyu Ma, Yasha Wang, Yang Lin, Junfeng Zhao, Liantao Ma
We lifted 8 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 |
|---|---|---|
| arthurleom/fgwmixup | canonical | 4 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| find_thresh | Ran | arthurleom/fgwmixup/src/gromov_mixup.py pointer only (licence: NONE) · get_code("ff00a877e232a9f9") |
| mixup_cross_entropy_loss | Ran | arthurleom/fgwmixup/src/gmixup_dgl.py pointer only (licence: NONE) · get_code("41a05f2d69abefee") |
| prepare_dataset_onehot_y | Ran | arthurleom/fgwmixup/src/gmixup_dgl.py pointer only (licence: NONE) · get_code("8f07b4faace68a1e") |
| sp_to_adjency | Ran | arthurleom/fgwmixup/src/gromov_mixup.py pointer only (licence: NONE) · get_code("cd2b9d7aab3484d9") |
| FGWMixup | Not yet run | arthurleom/fgwmixup/src/gromov_mixup.py pointer only (licence: NONE) · get_code("798334f7fa9c3e30") |
| fused_ACC_numpy | Not yet run | arthurleom/fgwmixup/src/gromov_mixup.py pointer only (licence: NONE) · get_code("e5a45fb33e3d635c") |
| my_fgw_barycenters | Not yet run | arthurleom/fgwmixup/src/gromov_mixup.py pointer only (licence: NONE) · get_code("3e8ac7d25aef9917") |
| prepare_dataset_x | Not yet run | arthurleom/fgwmixup/src/gmixup_dgl.py pointer only (licence: NONE) · get_code("8fa4bfa83d1f845f") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals. To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a "midpoint" of source graphs in the Fused Gromov-Wasserstein (FGW) metric space. To enhance the scalability of our method, we introduce a relaxed FGW solver that accelerates FGWMixup by improving the convergence rate from O(t -1 ) to O(t -2 ). Extensive experiments conducted on five datasets using both classic (MPNNs) and advanced (Graphormers) GNN backbones demonstrate that FGWMixup effectively improves the generalizability and robustness of GNNs. Codes are available at https://github.com/ArthurLeoM/FGWMixup.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2306.15963")
get_code_for_paper("2306.15963")
have("2306.15963")
Connect an agent — have() is free.