Arie Soeteman, Balder Ten Cate
We lifted 8 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 |
|---|---|---|
| ariesoeteman/hegnn | canonical | 0 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| array_list_to_tensor_list | Not yet run | ariesoeteman/hegnn/hegnn/data_processing/hdf5_structures.py code served (permissive licence) · get_code("5f06c3eac54e5a1a") |
| count_cycles | Not yet run | ariesoeteman/hegnn/hegnn/data_processing/cycle_counts.py code served (permissive licence) · get_code("741b7ffa6d75215b") |
| merge_batch_list | Not yet run | ariesoeteman/hegnn/hegnn/data_processing/data_structures.py code served (permissive licence) · get_code("f46e7cceda763952") |
| recursive_dict_update | Not yet run | ariesoeteman/hegnn/hegnn/config/parse_config.py code served (permissive licence) · get_code("efbd80279eae3407") |
| square_edge_index | Not yet run | ariesoeteman/hegnn/hegnn/data_processing/data_preprocessing.py code served (permissive licence) · get_code("1df314f5090b4621") |
| square_x | Not yet run | ariesoeteman/hegnn/hegnn/data_processing/data_preprocessing.py code served (permissive licence) · get_code("7486d5df90e40102") |
| to_numpy | Not yet run | ariesoeteman/hegnn/hegnn/data_processing/hdf5_structures.py code served (permissive licence) · get_code("a0d88b4d6461590b") |
| to_tensor | Not yet run | ariesoeteman/hegnn/hegnn/data_processing/hdf5_structures.py code served (permissive licence) · get_code("273d3b1783ffc1ae") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose and study Hierarchical Ego Graph Neural Networks (HE-GNNs), an expressive extension of graph neural networks (GNNs) with hierarchical node individualization, inspired by the Individualization-Refinement paradigm for isomorphism testing. HE-GNNs generalize subgraph-GNNs and form a hierarchy of increasingly expressive models that, in the limit, distinguish graphs up to isomorphism. We show that, over graphs of bounded degree, the separating power of HE-GNN node classifiers equals that of graded hybrid logic. This characterization enables us to relate the separating power of HE-GNNs to that of higher-order GNNs, GNNs enriched with local homomorphism count features, and color refinement algorithms based on Individualization-Refinement. Our experimental results confirm the practical feasibility of HE-GNNs and show benefits in comparison with traditional GNN architectures, both with and without local homomorphism count features.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2506.13911")
get_code_for_paper("2506.13911")
have("2506.13911")
Connect an agent — have() is free.