Papers › N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules

N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules

24 Jun 2018NeurIPS 2019 12arXiv:1806.09206archive 2025-07-28

Shengchao Liu, Mehmet Furkan Demirel, YIngyu Liang

Machine learning techniques have recently been adopted in various applications in medicine, biology, chemistry, and material engineering. An important task is to predict the properties of molecules, which serves as the main subroutine in many downstream applications such as virtual screening and drug design. Despite the increasing interest, the key challenge is to construct proper representations of molecules for learning algorithms. This paper introduces the N-gram graph, a simple unsupervised representation for molecules. The method first embeds the vertices in the molecule graph. It then constructs a compact representation for the graph by assembling the vertex embeddings in short walks in the graph, which we show is equivalent to a simple graph neural network that needs no training. The representations can thus be efficiently computed and then used with supervised learning methods for prediction. Experiments on 60 tasks from 10 benchmark datasets demonstrate its advantages over both popular graph neural networks and traditional representation methods. This is complemented by theoretical analysis showing its strong representation and prediction power.

PaperPDFConference PDFCodeCode 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="1806.09206")

Code

Syntology Ran 0 of 14 code samples harvested from 1 repository linked to this paper; 14 have no recorded run.

By repository: official repository: 14 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chao1224/n_gram_graph officialmentioned in papermentioned 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

14 samples harvested; 0 ran; 0 honoured the contract we drafted; 14 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.

14unverified

Licence: 0 of the 14 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 chao1224/n_gram_graph. “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.

eval_precision_auc_single chao1224/n_gram_graph/n_gram_graph/model/xgboost_classification.py official repository unverified MIT (permissive) · a84d48d3f4da50b2 · report
eval_roc_auc_single chao1224/n_gram_graph/n_gram_graph/model/xgboost_classification.py official repository unverified MIT (permissive) · ec25e146522eae7c · report
extract_atom_features chao1224/n_gram_graph/datasets/graph_util.py official repository unverified MIT (permissive) · a624692f0d5c694f · report
extract_feature_and_label chao1224/n_gram_graph/n_gram_graph/util.py official repository unverified MIT (permissive) · 54f60a5f224a43de · report
extract_feature_and_label_npy chao1224/n_gram_graph/n_gram_graph/util.py official repository unverified MIT (permissive) · d2486ecb7758cb18 · report
get_data chao1224/n_gram_graph/n_gram_graph/embedding/graph_embedding.py official repository unverified MIT (permissive) · 13577a7f893cffe2 · report
get_data chao1224/n_gram_graph/n_gram_graph/embedding/node_embedding.py official repository unverified MIT (permissive) · a71541d7e492251e · report
get_walk_representation chao1224/n_gram_graph/n_gram_graph/embedding/graph_embedding.py official repository unverified MIT (permissive) · b1f9ec0171283338 · report
one_of_k_encoding chao1224/n_gram_graph/datasets/graph_util.py official repository unverified MIT (permissive) · d8aa3b46875f660f · report
one_of_k_encoding_unk chao1224/n_gram_graph/datasets/graph_util.py official repository unverified MIT (permissive) · a0a187fc6d7c1fbb · report
precision_auc_single chao1224/n_gram_graph/n_gram_graph/evaluation.py official repository unverified MIT (permissive) · 722ce4106fe14cb6 · report
read_merged_data chao1224/n_gram_graph/n_gram_graph/util.py official repository unverified MIT (permissive) · 3ad2ab861692ccfa · report
rms_score chao1224/n_gram_graph/n_gram_graph/evaluation.py official repository unverified MIT (permissive) · 4e1ae6888f565413 · report
roc_auc_single chao1224/n_gram_graph/n_gram_graph/evaluation.py official repository unverified MIT (permissive) · 5b8eaedcb343dbd7 · report

Tasks

Drug DesignGraph Neural NetworkMolecular Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Molecular Property Prediction BACE N-GramXGB ROC-AUC 79.1 #13 of 20 Archive leaderboard report
Molecular Property Prediction BACE N-GramRF ROC-AUC 77.9 #14 of 20 Archive leaderboard report
Molecular Property Prediction BBBP N-GramRF ROC-AUC 69.7 #21 of 29 Archive leaderboard report
Molecular Property Prediction BBBP N-GramXGB ROC-AUC 69.1 #23 of 29 Archive leaderboard report
Molecular Property Prediction FreeSolv N-GramRF RMSE 2.688 #20 of 22 Archive leaderboard report
Molecular Property Prediction FreeSolv N-GramXGB RMSE 5.061 #22 of 22 Archive leaderboard report
Molecular Property Prediction Lipophilicity N-GramRF RMSE 0.812 #10 of 13 Archive leaderboard report
Molecular Property Prediction Lipophilicity N-GramXGB RMSE 2.072 #13 of 13 Archive leaderboard report
Molecular Property Prediction QM7 N-GramXGB MAE 81.9 #3 of 8 Archive leaderboard report
Molecular Property Prediction QM7 N-GramRF MAE 92.8 #5 of 8 Archive leaderboard report
Molecular Property Prediction QM8 N-GramXGB MAE 0.0215 #5 of 8 Archive leaderboard report
Molecular Property Prediction QM8 N-GramRF MAE 0.0236 #8 of 8 Archive leaderboard report
Molecular Property Prediction QM9 N-GramXGB MAE 0.00964 #5 of 8 Archive leaderboard report
Molecular Property Prediction QM9 N-GramRF MAE 0.01037 #8 of 8 Archive leaderboard report
Molecular Property Prediction SIDER N-GramRF ROC-AUC 66.8 #6 of 19 Archive leaderboard report
Molecular Property Prediction SIDER N-GramXGB ROC-AUC 65.5 #8 of 19 Archive leaderboard report
Molecular Property Prediction Tox21 N-GramXGB ROC-AUC 75.8 #12 of 20 Archive leaderboard report
Molecular Property Prediction Tox21 N-GramRF ROC-AUC 74.3 #13 of 20 Archive leaderboard report
Molecular Property Prediction clintox N-GramXGB ROC-AUC 87.5 #9 of 20 Archive leaderboard report
Molecular Property Prediction clintox N-GramRF ROC-AUC 77.5 #15 of 20 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