We lifted 10 functions out of this paper's own repositories and ran 9 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 |
|---|---|---|
| hyeonsoojo/metagc | canonical | 9 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| adarmic_adar | Ran | hyeonsoojo/metagc/utils/data_utils.py code served (permissive licence) · get_code("8df7821a89f8237c") |
| add_noise_edges | Ran | hyeonsoojo/metagc/utils/data_utils.py code served (permissive licence) · get_code("972f0874d70166c2") |
| modularity | Ran | hyeonsoojo/metagc/utils/metric.py code served (permissive licence) · get_code("3152f573a8af402b") |
| normalized_adj | Ran | hyeonsoojo/metagc/utils/load_utils.py code served (permissive licence) · get_code("69994d91ca12471e") |
| normalized_attributes | Ran | hyeonsoojo/metagc/utils/load_utils.py code served (permissive licence) · get_code("c4fbb25e66a33ccd") |
| pairwise_precision | Ran | hyeonsoojo/metagc/utils/metric.py code served (permissive licence) · get_code("10297a169f7e2aaa") |
| pairwise_recall | Ran | hyeonsoojo/metagc/utils/metric.py code served (permissive licence) · get_code("b7dbda02c4058c40") |
| parse_index_file | Ran | hyeonsoojo/metagc/utils/load_utils.py code served (permissive licence) · get_code("5c3fa9402a9405bc") |
| update_module | Ran | hyeonsoojo/metagc/utils/clone_utils.py code served (permissive licence) · get_code("2fe75f7f5b4e5ea9") |
| clone_module | Not yet run | hyeonsoojo/metagc/utils/clone_utils.py code served (permissive licence) · get_code("3425b06cc24cb577") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
How can we find meaningful clusters in a graph robustly against noise edges? Graph clustering (i.e., dividing nodes into groups of similar ones) is a fundamental problem in graph analysis with applications in various fields. Recent studies have demonstrated that graph neural network (GNN) based approaches yield promising results for graph clustering. However, we observe that their performance degenerates significantly on graphs with noise edges, which are prevalent in practice. In this work, we propose MetaGC for robust GNN-based graph clustering. MetaGC employs a decomposable clustering loss function, which can be rephrased as a sum of losses over node pairs. We add a learnable weight to each node pair, and MetaGC adaptively adjusts the weights of node pairs using meta-weighting so that the weights of meaningful node pairs increase and the weights of less-meaningful ones (e.g., noise edges) decrease. We show empirically that MetaGC learns weights as intended and consequently outperforms the state-of-the-art GNN-based competitors, even when they are equipped with separate denoising schemes, on five real-world graphs under varying levels of noise. Our code and datasets are available at https://github.com/HyeonsooJo/MetaGC.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.00322")
get_code_for_paper("2311.00322")
have("2311.00322")
Connect an agent — have() is free.