SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.09376 · 2021

Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 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.

RepositoryRoleRan
skepsun/SAGN_with_SLE canonical 5 of 6
FunctionStatusWhere it lives
entropy Ran skepsun/SAGN_with_SLE/src/utils.py
code served (permissive licence) · get_code("a4d2591506684852")
generate_preds_path Ran skepsun/SAGN_with_SLE/src/post_process.py
code served (permissive licence) · get_code("f31615a9e0aa6f97")
get_n_params Ran skepsun/SAGN_with_SLE/src/utils.py
code served (permissive licence) · get_code("c6acd3e400fc2676")
load_output_files Ran skepsun/SAGN_with_SLE/src/post_process.py
code served (permissive licence) · get_code("eb1a19a333b59f25")
to_scipy Ran skepsun/SAGN_with_SLE/src/utils.py
code served (permissive licence) · get_code("9301ba207b35bab1")
test Not yet run skepsun/SAGN_with_SLE/src/train_process.py
code served (permissive licence) · get_code("8ccc6f05779c9d3f")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

It is hard to directly implement Graph Neural Networks (GNNs) on large scaled graphs. Besides of existed neighbor sampling techniques, scalable methods decoupling graph convolutions and other learnable transformations into preprocessing and post classifier allow normal minibatch training. By replacing redundant concatenation operation with attention mechanism in SIGN, we propose Scalable and Adaptive Graph Neural Networks (SAGN). SAGN can adaptively gather neighborhood information among different hops. To further improve scalable models on semi-supervised learning tasks, we propose Self-Label-Enhance (SLE) framework combining self-training approach and label propagation in depth. We add base model with a scalable node label module. Then we iteratively train models and enhance train set in several stages. To generate input of node label module, we directly apply label propagation based on one-hot encoded label vectors without inner random masking. We find out that empirically the label leakage has been effectively alleviated after graph convolutions. The hard pseudo labels in enhanced train set participate in label propagation with true labels. Experiments on both inductive and transductive datasets demonstrate that, compared with other sampling-based and sampling-free methods, SAGN achieves better or comparable results and SLE can further improve performance.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.09376")
get_code_for_paper("2104.09376")
have("2104.09376")

Connect an agent — have() is free.