We lifted 9 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| tuanh23/e2eg | canonical | 5 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| call_instance_method | Ran | tuanh23/e2eg/pecos/utils/parallel_util.py code served (permissive licence) · get_code("2e9567bfa5f61827") |
| test | Ran | tuanh23/e2eg/baseline_models/gnn.py code served (permissive licence) · get_code("8e6629dff4ea0a71") |
| test | Ran | tuanh23/e2eg/baseline_models/mlp.py code served (permissive licence) · get_code("11767d5189f43309") |
| train | Ran | tuanh23/e2eg/baseline_models/gnn.py code served (permissive licence) · get_code("82f54a95d4951b19") |
| train | Ran | tuanh23/e2eg/baseline_models/mlp.py code served (permissive licence) · get_code("fac9425843013f50") |
| cs_matrix | Not yet run | tuanh23/e2eg/pecos/utils/smat_util.py code served (permissive licence) · get_code("37212e852e7bfd7e") |
| csc_matrix | Not yet run | tuanh23/e2eg/pecos/utils/smat_util.py code served (permissive licence) · get_code("faf670547bb5166e") |
| csr_matrix | Not yet run | tuanh23/e2eg/pecos/utils/smat_util.py code served (permissive licence) · get_code("daec7637a492323b") |
| hierarchical_kmeans | Not yet run | tuanh23/e2eg/pecos/utils/cluster_util.py code served (permissive licence) · get_code("562620383e081fb5") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Node classification utilizing text-based node attributes has many real-world applications, ranging from prediction of paper topics in academic citation graphs to classification of user characteristics in social media networks. State-of-the-art node classification frameworks, such as GIANT, use a two-stage pipeline: first embedding the text attributes of graph nodes then feeding the resulting embeddings into a node classification model. In this paper, we eliminate these two stages and develop an end-to-end node classification model that builds upon GIANT, called End-to-End-GIANT (E2EG). The tandem utilization of a main and an auxiliary classification objectives in our approach results in a more robust model, enabling the BERT backbone to be switched out for a distilled encoder with a 25% - 40% reduction in the number of parameters. Moreover, the model's end-to-end nature increases ease of use, as it avoids the need of chaining multiple models for node classification. Compared to a GIANT+MLP baseline on the ogbn-arxiv and ogbn-products datasets, E2EG obtains slightly better accuracy in the transductive setting (+0.5%), while reducing model training time by up to 40%. Our model is also applicable in the inductive setting, outperforming GIANT+MLP by up to +2.23%.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2208.04609")
get_code_for_paper("2208.04609")
have("2208.04609")
Connect an agent — have() is free.