Papers › Graph as Point Set

Graph as Point Set

5 May 2024arXiv:2405.02795archive 2025-07-28

Xiyuan Wang, Pan Li, Muhan Zhang

Graph is a fundamental data structure to model interconnections between entities. Set, on the contrary, stores independent elements. To learn graph representations, current Graph Neural Networks (GNNs) primarily use message passing to encode the interconnections. In contrast, this paper introduces a novel graph-to-set conversion method that bijectively transforms interconnected nodes into a set of independent points and then uses a set encoder to learn the graph representation. This conversion method holds dual significance. Firstly, it enables using set encoders to learn from graphs, thereby significantly expanding the design space of GNNs. Secondly, for Transformer, a specific set encoder, we provide a novel and principled approach to inject graph information losslessly, different from all the heuristic structural/positional encoding methods adopted in previous graph transformers. To demonstrate the effectiveness of our approach, we introduce Point Set Transformer (PST), a transformer architecture that accepts a point set converted from a graph as input. Theoretically, PST exhibits superior expressivity for both short-range substructure counting and long-range shortest path distance tasks compared to existing GNNs. Extensive experiments further validate PST's outstanding real-world performance. Besides Transformer, we also devise a Deepset-based set encoder, which achieves performance comparable to representative GNNs, affirming the versatility of our graph-to-set method.

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 27 code samples harvested from 1 repository linked to this paper: 20 ran (of which 15 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 27 samples from 1 repository, 20 ran (16 with no instrument failure; 4 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

GraphPKU/GraphAsSet officialmentioned on GitHubpytorchSyntology: 27 samples, 20 ran (4 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

27 samples harvested: 20 ran (of which 15 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 4 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 · our draft was wrong
15ran
7unverified

Licence: 27 of the 27 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 GraphPKU/GraphAsSet. “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 12 samples 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.

GraphPKU/GraphAsSet official repository 27 samples, 20 ran (4 instrument-failed) · 7 unverified
BatchNorm in 19 papers PST.py ran no licence file found · pointer only · 940703b780d57034 · report fixture: returned BatchNorm · level recorded 2026-09-22
DirCFConv PST.py ran no licence file found · pointer only · 227dca0b1ddd8a86 · report fixture: returned DirCFConv · level recorded 2026-09-22
GaussianGaussian PST.py ran fingerprinted no licence file found · pointer only · c743aa96864dc381 · report fixture: returned GaussianGaussian · level recorded 2026-09-22
GaussianSmearing PST.py ran fingerprinted no licence file found · pointer only · a23408f1e809e4da · report fixture: returned GaussianSmearing · level recorded 2026-09-22
IdEncoding PST.py ran fingerprinted no licence file found · pointer only · f9c8f5c4b824c8c5 · report fixture: returned IdEncoding · level recorded 2026-09-22
InstanceNorm in 6 papers PST.py ran fingerprinted no licence file found · pointer only · e4a9148d065dfe3f · report fixture: returned InstanceNorm · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
PST.py ran no licence file found · pointer only · 1de67bb52895024c · report fixture: returned LayerNorm · level recorded 2026-09-22
MLP in 375 papers PST.py ran fingerprinted no licence file found · pointer only · b63c020d3cb4419d · report fixture: returned MLP · level recorded 2026-09-22
MLPEncoding PST.py ran fingerprinted no licence file found · pointer only · a669c0ab6a140900 · report fixture: returned MLPEncoding · level recorded 2026-09-22
MultiEmbedding PST.py ran no licence file found · pointer only · 09974265ed73cca2 · report fixture: returned MultiEmbedding · level recorded 2026-09-22
NoneNorm PST.py ran fingerprinted no licence file found · pointer only · f9b995922ba2b15d · report fixture: returned NoneNorm · level recorded 2026-09-22
Set2Vec PST.py ran no licence file found · pointer only · 4ecd1c09b35d2866 · report fixture: returned Set2Vec · level recorded 2026-09-22
SinEncoding PST.py ran fingerprinted no licence file found · pointer only · 2ca2fc1fb0f470ef · report fixture: returned SinEncoding · level recorded 2026-09-22
VMean PST.py ran fingerprinted no licence file found · pointer only · 671376fabd3398eb · report fixture: returned VMean · level recorded 2026-09-22
VNorm PST.py ran fingerprinted no licence file found · pointer only · c25b516cf38d203b · report fixture: returned VNorm · level recorded 2026-09-22
createemb PST.py ran · our draft was wrong no licence file found · pointer only · b4ea68a7c46241fb · report fixture: signature dim:int/0/int, emb_dim:int/0/int, zeropad:bool/0/bool, max_norm:float/0/float, orthoinit:bool/0/bool · returned Embedding · level recorded 2026-09-22
maskedMax PST.py ran · our draft was wrong no licence file found · pointer only · 7fc5dce859b3a9ed · report fixture: signature x:Tensor/2/float, mask:Tensor/2/bool, dim:int/0/int · returned Tensor · level recorded 2026-09-22
maskedMean PST.py ran · our draft was wrong no licence file found · pointer only · d6cc090e909513c3 · report fixture: signature x:Tensor/2/float, mask:Tensor/2/bool, dim:int/0/int, gsize:Tensor/1/int · returned Tensor · level recorded 2026-09-22
maskedSum PST.py ran · our draft was wrong no licence file found · pointer only · eadfb092195ff0c6 · report fixture: signature x:Tensor/2/float, mask:Tensor/2/bool, dim:int/0/int · returned Tensor · level recorded 2026-09-22
maskednone PST.py ran · honoured contract no licence file found · pointer only · 8575a32db62b46c6 · report fixture: signature x:Tensor/2/float, mask:Tensor/2/bool, dim:int/0/int · returned Tensor · level recorded 2026-09-22
Imod PST.py unverified no licence file found · pointer only · b81dc93e9346681b · report
PST PST.py unverified no licence file found · pointer only · c793a8c825a61eb6 · report
PermEquiLayer PST.py unverified no licence file found · pointer only · 71379d4107f0e6eb · report
QInputEncoder PST.py unverified no licence file found · pointer only · f104731798499118 · report
Set2Set PST.py unverified no licence file found · pointer only · 7d53b92370ae668a · report
sv2el PST.py unverified no licence file found · pointer only · 73e5dc6a7e9a564f · report
svMix PST.py unverified no licence file found · pointer only · 0f3d8abf4d3866c5 · 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 Point Set Transformer (PST) (graph method: Point Set Transformer (PST)). 27 bricks; individually on a fixture: 20 ran (of which 15 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. PST entry · level 0 · unverified · c793a8c825a61eb6
  2. DirCFConv model · level 1 · ran · 227dca0b1ddd8a86
  3. Imod helper · level 0 · unverified · b81dc93e9346681b
  4. MLP helper · level 1 · ran · b63c020d3cb4419d
  5. PermEquiLayer helper · level 0 · unverified · 71379d4107f0e6eb
  6. QInputEncoder helper · level 0 · unverified · f104731798499118
  7. VMean model · level 1 · ran · 671376fabd3398eb
  8. VNorm model · level 1 · ran · c25b516cf38d203b
  9. sv2el model · level 0 · unverified · 73e5dc6a7e9a564f
  10. svMix model · level 0 · unverified · 0f3d8abf4d3866c5
  11. NoneNorm helper · level 1 · ran · f9b995922ba2b15d
  12. Set2Set helper · level 0 · unverified · 7d53b92370ae668a
  13. Set2Vec helper · level 1 · ran · 4ecd1c09b35d2866
  14. MultiEmbedding helper · level 1 · ran · 09974265ed73cca2
  15. BatchNorm helper · level 1 · ran · 940703b780d57034
  16. createemb helper · level 1 · ran · our draft was wrong · b4ea68a7c46241fb
  17. GaussianGaussian helper · level 1 · ran · c743aa96864dc381
  18. GaussianSmearing helper · level 1 · ran · a23408f1e809e4da
  19. IdEncoding helper · level 1 · ran · f9c8f5c4b824c8c5
  20. InstanceNorm helper · level 1 · ran · e4a9148d065dfe3f
  21. LayerNorm helper · level 1 · ran · 1de67bb52895024c
  22. MLPEncoding helper · level 1 · ran · a669c0ab6a140900
  23. SinEncoding helper · level 1 · ran · 2ca2fc1fb0f470ef
  24. maskedMax helper · level 1 · ran · our draft was wrong · 7fc5dce859b3a9ed
  25. maskedMean helper · level 1 · ran · our draft was wrong · d6cc090e909513c3
  26. maskedSum helper · level 1 · ran · our draft was wrong · eadfb092195ff0c6
  27. maskednone helper · level 1 · ran · honoured contract · 8575a32db62b46c6

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="2405.02795") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSETSet TransformerSoftmaxTransformer

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