Papers › Are Graph Neural Networks Optimal Approximation Algorithms?

Are Graph Neural Networks Optimal Approximation Algorithms?

1 Oct 2023arXiv:2310.00526archive 2025-07-28

Morris Yau, Nikolaos Karalias, Eric Lu, Jessica Xu, Stefanie Jegelka

In this work we design graph neural network architectures that capture optimal approximation algorithms for a large class of combinatorial optimization problems, using powerful algorithmic tools from semidefinite programming (SDP). Concretely, we prove that polynomial-sized message-passing algorithms can represent the most powerful polynomial time algorithms for Max Constraint Satisfaction Problems assuming the Unique Games Conjecture. We leverage this result to construct efficient graph neural network architectures, OptGNN, that obtain high-quality approximate solutions on landmark combinatorial optimization problems such as Max-Cut, Min-Vertex-Cover, and Max-3-SAT. Our approach achieves strong empirical results across a wide range of real-world and synthetic datasets against solvers and neural baselines. Finally, we take advantage of OptGNN's ability to capture convex relaxations to design an algorithm for producing bounds on the optimal solution from the learned embeddings of OptGNN.

PaperPDFCodeCode Syntology ran

In Syntology 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="2310.00526")

Code

Syntology Ran 6 of 13 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

penlu/bespoke-gnn4do officialmentioned on GitHubpytorch 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

13 samples harvested; 6 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6ran
7unverified

Licence: 13 of the 13 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 penlu/bespoke-gnn4do. “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.

e1_projector penlu/bespoke-gnn4do/problem/baselines.py official repository ran no licence file found · pointer only · 49aa42235df7ad05 · report
featurize_batch penlu/bespoke-gnn4do/model/training.py official repository ran no licence file found · pointer only · f9504b4360b1518c · report
get_kamis_score penlu/bespoke-gnn4do/kamis.py official repository ran no licence file found · pointer only · 929c874577947a6d · report
max_cut_sdp penlu/bespoke-gnn4do/problem/baselines.py official repository ran no licence file found · pointer only · 893ec2c23d74dbf8 · report
random_orthogonal_matrix penlu/bespoke-gnn4do/utils/graph_utils.py official repository ran fingerprinted no licence file found · pointer only · 3409de43caa9035a · report
vertex_cover_obj penlu/bespoke-gnn4do/problem/losses.py official repository ran no licence file found · pointer only · 944467b97937b163 · report
gen_graph penlu/bespoke-gnn4do/utils/graph_utils.py official repository unverified no licence file found · pointer only · f902914db1ae1dbd · report
get_validation_score penlu/bespoke-gnn4do/kamis.py official repository unverified no licence file found · pointer only · 0139feb1ee03cd3b · report
load_model penlu/bespoke-gnn4do/model/saving.py official repository unverified no licence file found · pointer only · 87983881cde22896 · report
max_cut_obj penlu/bespoke-gnn4do/problem/losses.py official repository unverified no licence file found · pointer only · 84ae23bf65494964 · report
predict penlu/bespoke-gnn4do/model/training.py official repository unverified no licence file found · pointer only · 0c645b2295bbb309 · report
random_rotation penlu/bespoke-gnn4do/utils/graph_utils.py official repository unverified no licence file found · pointer only · f19e1cf876592813 · report
vertex_cover_constraint penlu/bespoke-gnn4do/problem/losses.py official repository unverified no licence file found · pointer only · 98b652e02b8b5fe2 · report

Tasks

Combinatorial OptimizationGraph Neural Network

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Graph Neural Network

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