Papers › Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

31 Jan 2022arXiv:2201.12987archive 2025-07-28

Siqi Miao, Miaoyuan Liu, Pan Li

Interpretable graph learning is in need as many scientific applications depend on learning models to collect insights from graph-structured data. Previous works mostly focused on using post-hoc approaches to interpret pre-trained models (graph neural networks in particular). They argue against inherently interpretable models because the good interpretability of these models is often at the cost of their prediction accuracy. However, those post-hoc methods often fail to provide stable interpretation and may extract features that are spuriously correlated with the task. In this work, we address these issues by proposing Graph Stochastic Attention (GSAT). Derived from the information bottleneck principle, GSAT injects stochasticity to the attention weights to block the information from task-irrelevant graph components while learning stochasticity-reduced attention to select task-relevant subgraphs for interpretation. The selected subgraphs provably do not contain patterns that are spuriously correlated with the task under some assumptions. Extensive experiments on eight datasets show that GSAT outperforms the state-of-the-art methods by up to 20%↑ in interpretation AUC and 5%↑ in prediction accuracy. Our code is available at https://github.com/Graph-COM/GSAT.

PaperPDFCodeCode Syntology ran

In Syntology 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="2201.12987")

Code

Syntology Ran 5 of 10 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Graph-COM/GSAT officialmentioned in papermentioned on GitHubpytorchMIT report
divelab/good mentioned on GitHubpytorchGPL-3.0 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

10 samples harvested; 5 ran; 1 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
3ran
5unverified

Licence: 0 of the 10 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 Graph-COM/GSAT. “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.

compute_adjacency_matrix_images Graph-COM/GSAT/src/datasets/mnist.py official repository ran fingerprinted MIT (permissive) · f61cb17009c83363 · report
list_to_torch Graph-COM/GSAT/src/datasets/mnist.py official repository ran MIT (permissive) · 88a529db78fde884 · report
read_file Graph-COM/GSAT/src/datasets/graph_sst2.py official repository ran · honoured contract MIT (permissive) · 60ccd1c98038811b · report
split Graph-COM/GSAT/src/datasets/graph_sst2.py official repository ran MIT (permissive) · fe7d97d9abf11937 · report
undirected_graph Graph-COM/GSAT/src/datasets/graph_sst2.py official repository ran · our draft was wrong MIT (permissive) · dde52a0f318548b4 · report
eval_one_batch Graph-COM/GSAT/src/pretrain_clf.py official repository unverified MIT (permissive) · 58d024fc97883157 · report
get_loaders_and_test_set Graph-COM/GSAT/src/utils/get_data_loaders.py official repository unverified MIT (permissive) · 1b2c93892e91d26d · report
get_random_split_idx Graph-COM/GSAT/src/utils/get_data_loaders.py official repository unverified MIT (permissive) · 748ff6aa4827bf6f · report
read_ba2motif_data Graph-COM/GSAT/src/datasets/ba_2motifs.py official repository unverified MIT (permissive) · 04d8e2c1ac682160 · report
train_one_batch Graph-COM/GSAT/src/pretrain_clf.py official repository unverified MIT (permissive) · 7e9b6145faddfc72 · report

Tasks

Graph Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Property Prediction ogbg-molhiv GSAT Ext. data No #11 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GSAT Number of params 249602 #11 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GSAT Test ROC-AUC 0.8067 ± 0.0950 #11 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GSAT Validation ROC-AUC 0.8347 ± 0.0031 #11 of 43 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