We lifted 2 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| yeweiysh/ihgnn | canonical | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| gnn_spmm | Ran | yeweiysh/ihgnn/lib/pytorch_util.py code served (permissive licence) · get_code("60fc5a60fd9bb303") |
| load_data | Not yet run | yeweiysh/ihgnn/util.py code served (permissive licence) · get_code("7911d0729f43e070") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Graph Neural Networks (GNNs) often assume strong homophily for graph classification, seldom considering heterophily, which means connected nodes tend to have different class labels and dissimilar features. In real-world scenarios, graphs may have nodes that exhibit both homophily and heterophily. Failing to generalize to this setting makes many GNNs underperform in graph classification. In this paper, we address this limitation by identifying three effective designs and develop a novel GNN architecture called IHGNN (short for Incorporating Heterophily into Graph Neural Networks). These designs include the combination of integration and separation of the ego- and neighbor-embeddings of nodes, adaptive aggregation of node embeddings from different layers, and differentiation between different node embeddings for constructing the graph-level readout function. We empirically validate IHGNN on various graph datasets and demonstrate that it outperforms the state-of-the-art GNNs for graph classification.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.07678")
get_code_for_paper("2203.07678")
have("2203.07678")
Connect an agent — have() is free.