Papers › GFT: Graph Foundation Model with Transferable Tree Vocabulary

GFT: Graph Foundation Model with Transferable Tree Vocabulary

9 Nov 2024arXiv:2411.06070archive 2025-07-28

Zehong Wang, Zheyuan Zhang, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye

Inspired by the success of foundation models in applications such as ChatGPT, as graph data has been ubiquitous, one can envision the far-reaching impacts that can be brought by Graph Foundation Models (GFMs) with broader applications in the areas such as scientific research, social network analysis, drug discovery, and e-commerce. Despite the significant progress of pre-trained graph neural networks, there haven't been GFMs that can achieve desired performance on various graph-learning-related tasks. Building GFMs may rely on a vocabulary that encodes transferable patterns shared among different tasks and domains. Unlike image and text, defining such transferable patterns for graphs remains an open question. In this paper, we aim to bridge this gap by rethinking the transferable patterns on graphs as computation trees -- i.e., tree structures derived from the message-passing process. Based on this insight, we propose a cross-task, cross-domain graph foundation model named GFT, short for Graph Foundation model with transferable Tree vocabulary. By treating computation trees as tokens within the transferable vocabulary, GFT improves model generalization and reduces the risk of negative transfer. The theoretical analyses and extensive experimental studies have demonstrated the transferability of computation trees and shown the effectiveness of GFT across diverse tasks and domains in graph learning. The open source code and data are available at https://github.com/Zehong-Wang/GFT.

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 25 code samples harvested from 2 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 17 ran (6 with no instrument failure; 11 where Syntology's instrument failed); community: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 18 samples that ran have no recorded date.

zehong-wang/gft officialmentioned in papermentioned on GitHubpytorchMITSyntology: 24 samples, 17 ran (11 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

25 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 12 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · violated contract
8ran · our draft was wrong
4ran; the contract check could not run
3ran
7unverified

Licence: 10 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

zehong-wang/gft official repository 24 samples, 17 ran (11 instrument-failed) · 7 unverified
ArxivFSSplitter GFT/dataset/task_constructor.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 5f925b34de0a38cb · report fixture: returned dict · level recorded 2026-09-26
CiteSplitter GFT/dataset/task_constructor.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 840cce4bf1e34557 · report fixture: signature dataset:MockDataset/0/? · returned dict · level recorded 2026-09-26
batched_embedding GFT/model/vq.py ran; the contract check could not run (RAISES) MIT (permissive) · 4dc1339e961ab500 · report fixture: signature indices:Tensor/3/int, embeds:Tensor/3/float · returned Tensor · level recorded 2026-09-22
binary_apr_func GFT/dataset/data_utils.py ran MIT (permissive) here; the stored copy is pointer only · 352a58f5914509ef · report fixture: signature func:MockFunc/0/?, output:Tensor/2/float, batch:MockBatch/0/? · returned Tensor · level recorded 2026-09-26
binary_single_auc_func GFT/dataset/data_utils.py ran MIT (permissive) here; the stored copy is pointer only · c06eaa1bc9d830c1 · report fixture: signature func:MockMetric/0/?, output:Tensor/2/float, batch:MockBatch/0/? · returned Tensor · level recorded 2026-09-26
cdist in 13 papers GFT/model/vq.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 4b4182a1077e1685 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-22
default in 430 papers GFT/model/ft_model.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is 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
GFT/model/ft_model.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
filter_unnecessary_attrs GFT/dataset/process_datasets.py ran MIT (permissive) here; the stored copy is pointer only · 6aa000a9e1b10057 · report fixture: signature dataset:MockDataset/0/?, mode:str/0/str · returned MockDataset · level recorded 2026-09-26
gumbel_sample in 15 papers
census: 6 implementations from 5 papers, 2 distinct outputs on one shared input
GFT/model/vq.py ran · our draft was wrong MIT (permissive) · 4755d07ad4a639cb · report fixture: signature logits:Tensor/2/float, temperature:float/0/float, stochastic:bool/0/bool, straight_through:bool/0/bool, reinmax:bool/0/bool, dim:int/0/int, training:bool/0/bool · returned tuple · level recorded 2026-09-22
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
GFT/model/vq.py ran · honoured contract fingerprinted MIT (permissive) · f3232418205f7cbd · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded, date not recorded
kmeans in 38 papers GFT/model/vq.py ran · our draft was wrong MIT (permissive) · 31974aebdb92319d · 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
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 2 of 2, arg 1: rank 2, kind float, dtype float32
GFT/model/vq.py ran · our draft was wrong fingerprinted MIT (permissive) · 702d64c397294ae2 · report fixture: signature x:Tensor/2/float, n_categories:int/0/int, eps:float/0/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
orthogonal_loss_fn GFT/model/vq.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 690fb00cdadafe62 · report fixture: signature t:Tensor/3/float · returned Tensor · level recorded 2026-09-22
refine_dataset GFT/dataset/process_datasets.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 58d48991c9718144 · report fixture: signature dataset:MockDataset/0/? · returned MockDataset · level recorded 2026-09-26
sample_vectors_distributed GFT/model/vq.py ran; the contract check could not run (RAISES) MIT (permissive) · ecf368eff22730c4 · report fixture: signature local_samples:Tensor/3/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
span_node_and_edge_idx GFT/dataset/process_datasets.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fe5ac93ea96ea352 · report fixture: signature dataset:Dataset/0/? · returned Dataset · level recorded 2026-09-26
CosineSimCodebook in 5 papers GFT/model/vq.py unverified MIT (permissive) · d8a07f536f522526 · report
EuclideanCodebook in 6 papers GFT/model/vq.py unverified MIT (permissive) · 74f95d115c4d707c · report
VectorQuantize in 6 papers GFT/model/vq.py unverified MIT (permissive) · 33b21e2fd12163eb · report
ema_inplace GFT/model/vq.py unverified MIT (permissive) · fda38ab65bb996a9 · report
flat_auc GFT/dataset/data_utils.py unverified MIT (permissive) here; the stored copy is pointer only · 1ae9c9bd82345553 · report
pack_one in 14 papers GFT/model/vq.py unverified MIT (permissive) · 9adcac32b9f87dfb · report
unpack_one in 8 papers GFT/model/vq.py unverified MIT (permissive) · 95a567bd7c1ffdce · report
thu-ml/GFT community 1 sample, 1 ran (1 instrument-failed) · 0 unverified
creat_optimizer in 5 papers LlamaGen/autoregressive/train/GFT_c2i.py ran · our draft was wrong MIT (permissive) · ba65976c1d96a7cb · report fixture: signature model:callable/0/?, weight_decay:float/0/float, learning_rate:float/0/float, betas:tuple/1/float, logger:Logger/0/? · returned AdamW · level recorded, date not recorded

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 GFT (graph method: GFT). 28 bricks; individually on a fixture: 19 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 15 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. VectorQuantize entry · level 0 · unverified · 33b21e2fd12163eb
  2. CosineSimCodebook model · level 0 · unverified · d8a07f536f522526
  3. EuclideanCodebook model · level 0 · unverified · 74f95d115c4d707c
  4. default helper · level 1 · ran · violated contract · 60fff7c3c400d7ff
  5. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  6. gumbel_sample sampler · level 1 · ran · our draft was wrong · 4755d07ad4a639cb
  7. identity helper · level 1 · ran · honoured contract · f3232418205f7cbd
  8. orthogonal_loss_fn loss · level 1 · ran; the contract check could not run (RAISES) · 690fb00cdadafe62
  9. pack_one helper · level 0 · unverified · 9adcac32b9f87dfb
  10. unpack_one helper · level 0 · unverified · 95a567bd7c1ffdce
  11. batched_embedding helper · level 1 · ran; the contract check could not run (RAISES) · 4dc1339e961ab500
  12. batched_sample_vectors helper · level 1 · ran; the contract check could not run · c1c89ffd41de10bb
  13. ema_inplace update_rule · level 0 · unverified · fda38ab65bb996a9
  14. kmeans model · level 1 · ran · our draft was wrong · 31974aebdb92319d
  15. l2norm helper · level 1 · ran · our draft was wrong · eca6cdf05972a95e
  16. laplace_smoothing helper · level 1 · ran · our draft was wrong · 702d64c397294ae2
  17. noop helper · level 0 · unverified · 02dd009b7cb924bb
  18. sample_vectors_distributed helper · level 1 · ran; the contract check could not run (RAISES) · ecf368eff22730c4
  19. uniform_init helper · level 0 · unverified · f9a12a99a3e74bc8
  20. cdist helper · level 1 · ran; the contract check could not run (RAISES) · 4b4182a1077e1685
  21. gumbel_noise helper · level 1 · ran · honoured contract · d85a55ec5c2984ef
  22. log helper · level 2 · ran · our draft was wrong · b5472673332de78e
  23. sample_vectors helper · level 1 · ran; the contract check could not run · ada1d74afbd92171
  24. batched_bincount helper · level 1 · ran · our draft was wrong · 309924b930360692
  25. all_gather_sizes helper · level 0 · unverified · cee1bd208302c3f3
  26. all_gather_variably_sized helper · level 1 · ran; the contract check could not run · 2e60cd798dd2182c
  27. sample_multinomial helper · level 1 · ran · our draft was wrong · cf379aef60d216c3
  28. pad_shape helper · level 1 · ran; the contract check could not run · 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="2411.06070") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Drug DiscoveryGraph Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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