Papers › Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation

Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation

17 Oct 2021ICLR 2022 4arXiv:2110.08727archive 2025-07-28

Shichang Zhang, Yozen Liu, Yizhou Sun, Neil Shah

Graph Neural Networks (GNNs) are popular for graph machine learning and have shown great results on wide node classification tasks. Yet, they are less popular for practical deployments in the industry owing to their scalability challenges incurred by data dependency. Namely, GNN inference depends on neighbor nodes multiple hops away from the target, and fetching them burdens latency-constrained applications. Existing inference acceleration methods like pruning and quantization can speed up GNNs by reducing Multiplication-and-ACcumulation (MAC) operations, but the improvements are limited given the data dependency is not resolved. Conversely, multi-layer perceptrons (MLPs) have no graph dependency and infer much faster than GNNs, even though they are less accurate than GNNs for node classification in general. Motivated by these complementary strengths and weaknesses, we bring GNNs and MLPs together via knowledge distillation (KD). Our work shows that the performance of MLPs can be improved by large margins with GNN KD. We call the distilled MLPs Graph-less Neural Networks (GLNNs) as they have no inference graph dependency. We show that GLNNs with competitive accuracy infer faster than GNNs by 146X-273X and faster than other acceleration methods by 14X-27X. Under a production setting involving both transductive and inductive predictions across 7 datasets, GLNN accuracies improve over stand-alone MLPs by 12.36% on average and match GNNs on 6/7 datasets. Comprehensive analysis shows when and why GLNNs can achieve competitive accuracies to GNNs and suggests GLNN as a handy choice for latency-constrained applications.

PaperPDFConference PDFCodeCode 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="2110.08727")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

snap-research/graphless-neural-networks 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

8 samples harvested; 7 ran; 0 honoured the contract we drafted; 1 has 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 · violated contract
1ran · our draft was wrong
5ran
1unverified

Licence: 8 of the 8 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 snap-research/graphless-neural-networks. “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_training_config snap-research/graphless-neural-networks/utils.py official repository ran MIT recorded; this copy not marked cleared · pointer only · 5b7ca3c80fc2a11a · report
idx_split snap-research/graphless-neural-networks/utils.py official repository ran MIT recorded; this copy not marked cleared · pointer only · ba7dbda11c083fd7 · report
is_binary_bag_of_words snap-research/graphless-neural-networks/data_preprocess.py official repository ran MIT recorded; this copy not marked cleared · pointer only · 77c12b26c7311bbd · report
normalize snap-research/graphless-neural-networks/data_preprocess.py official repository ran · violated contract MIT recorded; this copy not marked cleared · pointer only · aa9c29936dee40a7 · report
to_binary_bag_of_words snap-research/graphless-neural-networks/data_preprocess.py official repository ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · c1b14a7851940dca · report
train snap-research/graphless-neural-networks/train_and_eval.py official repository ran MIT recorded; this copy not marked cleared · pointer only · 2b547c0185564a58 · report
train_mini_batch snap-research/graphless-neural-networks/train_and_eval.py official repository ran MIT recorded; this copy not marked cleared · pointer only · 69640025673d56e1 · report
train_sage snap-research/graphless-neural-networks/train_and_eval.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · ee0ff9821725414f · report

Tasks

Knowledge DistillationNode ClassificationNode Property PredictionQuantization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification AMZ Computers GLNN Accuracy 83.03± 1.87% #5 of 5 Archive leaderboard report
Node Classification AMZ Photo GLNN Accuracy 92.11± 1.08% #11 of 14 Archive leaderboard report
Node Classification Citeseer GLNN Accuracy 71.77± 2.01 #50 of 71 Archive leaderboard report
Node Classification Cora GLNN Accuracy 80.54± 1.35% #64 of 73 Archive leaderboard report
Node Classification Pubmed GLNN Accuracy 75.42 ± 2.31 #63 of 70 Archive leaderboard report
Node Property Prediction ogbn-arxiv GLNN Test Accuracy 0.6346± 0.0045 #82 of 86 Archive leaderboard report
Node Property Prediction ogbn-products GLNN Test Accuracy 0.6886 ± 0.0046 #61 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.

Methods

Knowledge DistillationPruningSPEED

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