Papers › VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

4 Aug 2023arXiv:2308.02117archive 2025-07-28

Ling Yang, Ye Tian, Minkai Xu, Zhongyi Liu, Shenda Hong, Wei Qu, Wentao Zhang, Bin Cui, Muhan Zhang, Jure Leskovec

GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output representations of teacher GNN. Existing methods mainly make the MLP to mimic the GNN predictions over a few class labels. However, the class space may not be expressive enough for covering numerous diverse local graph structures, thus limiting the performance of knowledge transfer from GNN to MLP. To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse local structures for GNN-to-MLP distillation. Specifically, we propose a variant of VQ-VAE to learn a structure-aware tokenizer on graph data that can encode each node's local substructure as a discrete code. The discrete codes constitute a codebook as a new graph representation space that is able to identify different local graph structures of nodes with the corresponding code indices. Then, based on the learned codebook, we propose a new distillation target, namely soft code assignments, to directly transfer the structural knowledge of each node from GNN to MLP. The resulting framework VQGraph achieves new state-of-the-art performance on GNN-to-MLP distillation in both transductive and inductive settings across seven graph datasets. We show that VQGraph with better performance infers faster than GNNs by 828x, and also achieves accuracy improvement over GNNs and stand-alone MLPs by 3.90% and 28.05% on average, respectively. Code: https://github.com/YangLing0818/VQGraph.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 30 code samples harvested from 1 repository linked to this paper: 23 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 4 violated, 5 with no contract checked; 13 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 8 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 30 samples from 1 repository, 23 ran (10 with no instrument failure; 13 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 23 samples that ran have no recorded date.

yangling0818/vqgraph officialmentioned in papermentioned on GitHubpytorchSyntology: 30 samples, 23 ran (13 instrument-failed) · 7 unverified 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

30 samples harvested: 23 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 4 violated, 5 with no contract checked; 13 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
4ran · violated contract
5ran · our draft was wrong
8ran; the contract check could not run
5ran
7unverified

Licence: 30 of the 30 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 yangling0818/vqgraph. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

yangling0818/vqgraph official repository 30 samples, 23 ran (13 instrument-failed) · 7 unverified
CosineSimCodebook in 5 papers vq.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0b4fc7f49d1b58ba · report fixture: returned CosineSimCodebook · level recorded 2026-09-22
all_gather_variably_sized vq.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 2e60cd798dd2182c · report fixture: signature x:Tensor/2/float, sizes:list/1/int, dim:int/0/int · returned list · level recorded 2026-09-22
batched_bincount in 5 papers vq.py ran · our draft was wrong no licence file found · pointer only · 309924b930360692 · report fixture: signature x:Tensor/2/int, minlength:int/0/int · returned Tensor · level recorded 2026-09-22
batched_embedding vq.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 5ebe8a85905da07b · report fixture: signature indices:Tensor/3/int, embeds:Tensor/3/float · returned Tensor · level recorded 2026-09-22
batched_sample_vectors vq.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · c1c89ffd41de10bb · report fixture: signature samples:Tensor/3/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
default in 430 papers vq.py ran · violated contract fingerprinted no licence file found · pointer only · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
vq.py ran · violated contract no licence file found · pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
get_training_config utils.py ran no licence file found · pointer only · 5b7ca3c80fc2a11a · report fixture: signature config_path:str/0/str, model_name:str/0/str, dataset:str/0/str · returned dict · level recorded 2026-09-24
gumbel_noise in 11 papers
census: 6 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vq.py ran · honoured contract fingerprinted no licence file found · pointer only · d85a55ec5c2984ef · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gumbel_sample in 15 papers
census: 6 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vq.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · b91addd507f9e21a · report fixture: signature t:Tensor/2/float, temperature:float/0/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
idx_split utils.py ran no licence file found · pointer only · ba7dbda11c083fd7 · report fixture: signature idx:Tensor/1/int, ratio:float/0/float, seed:int/0/int · returned tuple · level recorded 2026-09-24
is_binary_bag_of_words data_preprocess.py ran no licence file found · pointer only · 77c12b26c7311bbd · report fixture: signature features:csr_matrix/2/float · returned bool · level recorded 2026-09-24
kmeans in 38 papers vq.py ran · our draft was wrong no licence file found · pointer only · aa0a7d67c59e2d8b · report fixture: signature samples:Tensor/3/float, num_clusters:int/0/int, num_iters:int/0/int, use_cosine_sim:bool/0/bool, sample_fn:callable/0/?, all_reduce_fn:callable/0/? · returned tuple · level recorded 2026-09-22
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vq.py ran · our draft was wrong fingerprinted no licence file found · pointer only · eca6cdf05972a95e · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded, date not recorded
laplace_smoothing in 8 papers
census: 3 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float32
vq.py ran · violated contract no licence file found · pointer only · b5240484210b398a · report fixture: signature x:Tensor/1/float, n_categories:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
data_preprocess.py ran · violated contract no licence file found · pointer only · aa9c29936dee40a7 · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
orthogonal_loss_fn vq.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 527a2ecf26715268 · report fixture: signature t:Tensor/3/float · returned Tensor · level recorded 2026-09-22
pad_shape vq.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 64ec7553b1fd0e74 · report fixture: signature shape:list/1/int, size:int/0/int, dim:int/0/int · returned list · level recorded 2026-09-22
sample_multinomial vq.py ran · our draft was wrong no licence file found · pointer only · cf379aef60d216c3 · report fixture: signature total_count:int/0/int, probs:Tensor/1/float · returned Tensor · level recorded 2026-09-22
sample_vectors in 15 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vq.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · ada1d74afbd92171 · report fixture: signature samples:Tensor/2/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
sample_vectors_distributed vq.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 1ec5828275165f9e · report fixture: signature local_samples:Tensor/3/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
to_binary_bag_of_words in 5 papers data_preprocess.py ran · our draft was wrong no licence file found · pointer only · c1b14a7851940dca · report fixture: signature features:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
train_mini_batch train_and_eval.py ran no licence file found · pointer only · 7a052a0b26ca317a · report fixture: signature model:callable/0/?, feats:Tensor/2/float, labels:Tensor/1/int, batch_size:int/0/int, criterion:callable/0/?, optimizer:SGD/0/?, lamb:int/0/int · returned float · level recorded 2026-09-24
EuclideanCodebook in 6 papers vq.py unverified no licence file found · pointer only · b6e2f12aa29482a4 · report
VectorQuantize in 6 papers vq.py unverified no licence file found · pointer only · 81cfe04feebb1487 · report
all_gather_sizes vq.py unverified no licence file found · pointer only · cee1bd208302c3f3 · report
noop in 15 papers vq.py unverified no licence file found · pointer only · 02dd009b7cb924bb · report
train in 522 papers train_and_eval.py unverified no licence file found · pointer only · be348e82ea1b9cc3 · report
train_sage train_and_eval.py unverified no licence file found · pointer only · c5f57af6d7f73831 · report
uniform_init in 10 papers vq.py unverified no licence file found · pointer only · f9a12a99a3e74bc8 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for VQGRAPH (graph method: VQGRAPH). 23 bricks; individually on a fixture: 18 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 3 violated, 1 with no contract checked; 13 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. VectorQuantize entry · level 0 · unverified · 81cfe04feebb1487
  2. CosineSimCodebook helper · level 1 · ran · 0b4fc7f49d1b58ba
  3. EuclideanCodebook helper · level 0 · unverified · b6e2f12aa29482a4
  4. default helper · level 1 · ran · violated contract · 60fff7c3c400d7ff
  5. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  6. orthogonal_loss_fn loss · level 1 · ran; the contract check could not run (RAISES) · 527a2ecf26715268
  7. batched_embedding helper · level 1 · ran; the contract check could not run (RAISES) · 5ebe8a85905da07b
  8. batched_sample_vectors helper · level 1 · ran; the contract check could not run (RAISES) · c1c89ffd41de10bb
  9. gumbel_sample helper · level 1 · ran; the contract check could not run (RAISES) · b91addd507f9e21a
  10. kmeans helper · level 1 · ran · our draft was wrong · aa0a7d67c59e2d8b
  11. l2norm helper · level 1 · ran · our draft was wrong · eca6cdf05972a95e
  12. noop helper · level 0 · unverified · 02dd009b7cb924bb
  13. sample_vectors_distributed helper · level 1 · ran; the contract check could not run (RAISES) · 1ec5828275165f9e
  14. uniform_init helper · level 0 · unverified · f9a12a99a3e74bc8
  15. laplace_smoothing helper · level 1 · ran · violated contract · b5240484210b398a
  16. sample_vectors helper · level 1 · ran; the contract check could not run (RAISES) · ada1d74afbd92171
  17. gumbel_noise helper · level 1 · ran · honoured contract · d85a55ec5c2984ef
  18. batched_bincount helper · level 1 · ran · our draft was wrong · 309924b930360692
  19. all_gather_sizes helper · level 0 · unverified · cee1bd208302c3f3
  20. all_gather_variably_sized helper · level 1 · ran; the contract check could not run (RAISES) · 2e60cd798dd2182c
  21. sample_multinomial helper · level 1 · ran · our draft was wrong · cf379aef60d216c3
  22. log helper · level 2 · ran · our draft was wrong · b5472673332de78e
  23. pad_shape helper · level 1 · ran; the contract check could not run (RAISES) · 64ec7553b1fd0e74

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2308.02117") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Knowledge DistillationQuantizationTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge DistillationVQ-VAE

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