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

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

19 Apr 2021arXiv:2104.09376archive 2025-07-28

Chuxiong Sun, Hongming Gu, Jie Hu

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2104.09376")

Code

Syntology Ran 1 of 6 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

skepsun/SAGN_with_SLE officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 1 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran
5unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from skepsun/SAGN_with_SLE. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_n_params skepsun/SAGN_with_SLE/src/utils.py official repository ran MIT (permissive) · c6acd3e400fc2676 · report
entropy skepsun/SAGN_with_SLE/src/utils.py official repository unverified MIT (permissive) · a4d2591506684852 · report
generate_preds_path skepsun/SAGN_with_SLE/src/post_process.py official repository unverified MIT (permissive) · f31615a9e0aa6f97 · report
load_output_files skepsun/SAGN_with_SLE/src/post_process.py official repository unverified MIT (permissive) · eb1a19a333b59f25 · report
test skepsun/SAGN_with_SLE/src/train_process.py official repository unverified MIT (permissive) · 8ccc6f05779c9d3f · report
to_scipy skepsun/SAGN_with_SLE/src/utils.py official repository unverified MIT (permissive) · 9301ba207b35bab1 · report

Tasks

Node Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Property Prediction ogbn-mag NARS_SAGN+SLE Ext. data No #16 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag NARS_SAGN+SLE Number of params 3846330 #16 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag NARS_SAGN+SLE Test Accuracy 0.5440 ± 0.0015 #16 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag NARS_SAGN+SLE Validation Accuracy 0.5591 ± 0.0017 #16 of 39 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE (4 stages) Ext. data No #4 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE (4 stages) Number of params 8556888 #4 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE (4 stages) Test Accuracy 0.6830 ± 0.0008 #4 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE (4 stages) Validation Accuracy 0.7163 ± 0.0007 #4 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE Ext. data No #9 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE Number of params 8556888 #9 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE Test Accuracy 0.6800 ± 0.0015 #9 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN+SLE Validation Accuracy 0.7131 ± 0.0010 #9 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN Ext. data No #14 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN Number of params 6098092 #14 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN Test Accuracy 0.6675 ± 0.0084 #14 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SAGN Validation Accuracy 0.7034 ± 0.0099 #14 of 20 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages)+C&S Ext. data No #17 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages)+C&S Number of params 2179678 #17 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages)+C&S Test Accuracy 0.8485 ± 0.0010 #17 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages)+C&S Validation Accuracy 0.9302 ± 0.0003 #17 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages) Ext. data No #18 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages) Number of params 2179678 #18 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages) Test Accuracy 0.8468 ± 0.0012 #18 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE (4 stages) Validation Accuracy 0.9309 ± 0.0007 #18 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE Ext. data No #23 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE Number of params 2179678 #23 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE Test Accuracy 0.8428 ± 0.0014 #23 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN+SLE Validation Accuracy 0.9287 ± 0.0003 #23 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN Ext. data No #38 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN Number of params 2233391 #38 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN Test Accuracy 0.8120 ± 0.0007 #38 of 64 Archive leaderboard report
Node Property Prediction ogbn-products SAGN Validation Accuracy 0.9309 ± 0.0004 #38 of 64 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections