Papers › Expressive Power of Invariant and Equivariant Graph Neural Networks

Expressive Power of Invariant and Equivariant Graph Neural Networks

28 Jun 2020ICLR 2021 1arXiv:2006.15646archive 2025-07-28

Waïss Azizian, Marc Lelarge

Various classes of Graph Neural Networks (GNN) have been proposed and shown to be successful in a wide range of applications with graph structured data. In this paper, we propose a theoretical framework able to compare the expressive power of these GNN architectures. The current universality theorems only apply to intractable classes of GNNs. Here, we prove the first approximation guarantees for practical GNNs, paving the way for a better understanding of their generalization. Our theoretical results are proved for invariant GNNs computing a graph embedding (permutation of the nodes of the input graph does not affect the output) and equivariant GNNs computing an embedding of the nodes (permutation of the input permutes the output). We show that Folklore Graph Neural Networks (FGNN), which are tensor based GNNs augmented with matrix multiplication are the most expressive architectures proposed so far for a given tensor order. We illustrate our results on the Quadratic Assignment Problem (a NP-Hard combinatorial problem) by showing that FGNNs are able to learn how to solve the problem, leading to much better average performances than existing algorithms (based on spectral, SDP or other GNNs architectures). On a practical side, we also implement masked tensors to handle batches of graphs of varying sizes.

PaperPDFConference PDFCodeCode 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 14 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 6 ran (4 with no instrument failure; 2 where Syntology's instrument failed); community: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 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.

mlelarge/graph_neural_net officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 6 ran (2 instrument-failed) · 6 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

14 samples harvested: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 6 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.

2ran · our draft was wrong
6ran
6unverified

Licence: 2 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 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 3 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.

mlelarge/graph_neural_net official repository 12 samples, 6 ran (2 instrument-failed) · 6 unverified
GraphNorm models/blocks_emb.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 80b5dc122a661e5a · report fixture: returned GraphNorm · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
models/blocks_emb.py ran · metamorphic tier: well formed fingerprinted Apache-2.0 (permissive) · 9375f2695dc66fe0 · report fixture: returned Identity · level recorded 2026-09-22
Matmul models/blocks_emb.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 0ed647828cd8e7e6 · report fixture: signature xs1:Tensor/3/float, xs2:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MlpBlock_Real models/blocks_emb.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 4dfdc22b4a6ed295 · report fixture: returned MlpBlock_Real · level recorded 2026-09-22
base_model in 5 papers models/blocks_emb.py ran · our draft was wrong Apache-2.0 (permissive) · aa2de678f6c52280 · report fixture: signature original_features_num:int/0/int, num_blocks:int/0/int, in_features:int/0/int, out_features:int/0/int, depth_of_mlp:int/0/int, block:callable/0/?, constant_n_vertices:bool/0/bool · returned dict · level recorded 2026-09-22
block in 17 papers models/blocks_emb.py ran · our draft was wrong Apache-2.0 (permissive) · d7331e9b86e16f47 · report fixture: signature in_features:int/0/int, out_features:int/0/int, depth_of_mlp:int/0/int, constant_n_vertices:bool/0/bool · returned dict · level recorded 2026-09-22
Concat models/blocks_emb.py unverified Apache-2.0 (permissive) · 62b5e09668e8358b · report
MlpBlock_Real models/blocks_emb.py unverified Apache-2.0 (permissive) · 21bde57ff07e5dcc · report
_init_weights in 9 papers models/blocks_emb.py unverified Apache-2.0 (permissive) · db4528f69778c115 · report
base_model in 5 papers models/blocks_emb.py unverified Apache-2.0 (permissive) · ca9b98d9883fa747 · report
block in 17 papers models/blocks_emb.py unverified Apache-2.0 (permissive) · f93f27ccbc08cab8 · report
RuihongQiu/FGNN community 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Embedding2Score model.py ran no licence file found · pointer only · aec2fbd3811ade54 · report fixture: signature session_embedding:Tensor/2/float, all_item_embedding:callable/0/?, batch:Tensor/1/int · returned Tensor · level recorded 2026-09-24
GNNModel model.py ran · metamorphic tier: deterministic no licence file found · pointer only · b54a3cbf74014993 · report fixture: returned GNNModel · level recorded 2026-09-22

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 Folklore Graph Neural Networks (FGNN) (graph method: Folklore Graph Neural Networks (FGNN)). 9 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. base_model entry · level 0 · unverified · ca9b98d9883fa747
  2. Identity helper · level 1 · ran · 9375f2695dc66fe0
  3. block model · level 1 · ran · our draft was wrong · d7331e9b86e16f47
  4. Concat helper · level 0 · unverified · 62b5e09668e8358b
  5. Matmul helper · level 1 · ran · 0ed647828cd8e7e6
  6. MlpBlock_Real helper · level 1 · ran · 4dfdc22b4a6ed295
  7. GraphNorm helper · level 1 · ran · 80b5dc122a661e5a
  8. _init_weights helper · level 0 · unverified · db4528f69778c115
  9. normalize helper · level 0 · unverified · 9219da3439a2613c

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="2006.15646") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph Embedding

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