Papers › DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems

DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems

8 Oct 2022arXiv:2210.04123archive 2025-07-28

Ruizhong Qiu, Zhiqing Sun, Yiming Yang

Recently, deep reinforcement learning (DRL) models have shown promising results in solving NP-hard Combinatorial Optimization (CO) problems. However, most DRL solvers can only scale to a few hundreds of nodes for combinatorial optimization problems on graphs, such as the Traveling Salesman Problem (TSP). This paper addresses the scalability challenge in large-scale combinatorial optimization by proposing a novel approach, namely, DIMES. Unlike previous DRL methods which suffer from costly autoregressive decoding or iterative refinements of discrete solutions, DIMES introduces a compact continuous space for parameterizing the underlying distribution of candidate solutions. Such a continuous space allows stable REINFORCE-based training and fine-tuning via massively parallel sampling. We further propose a meta-learning framework to enable the effective initialization of model parameters in the fine-tuning stage. Extensive experiments show that DIMES outperforms recent DRL-based methods on large benchmark datasets for Traveling Salesman Problems and Maximal Independent Set problems.

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.

Syntology holds a reference implementation of DIMES, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='DIMES') (how to connect); the free check have('2210.04123') needs no token.

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

Code

Syntology 25 code samples harvested from 1 repository linked to this paper: 10 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 10 ran (1 with no instrument failure; 9 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.

dimesteam/dimes officialmentioned in papermentioned on GitHubpytorchSyntology: 25 samples, 10 ran (9 instrument-failed) · 15 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: 10 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 15 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.

9ran · our draft was wrong
1ran
15unverified

Licence: 0 of the 25 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 dimesteam/dimes. “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”. “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.

dimesteam/dimes official repository 25 samples, 10 ran (9 instrument-failed) · 15 unverified
Model in 227 papers MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran MIT (permissive) · bcdee00b1c1f4959 · report fixture: returned Model · level recorded 2026-09-22
apply_norm MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · 2e790af504140ec1 · report fixture: signature x:SymbolicTensor/2/float, scale:SymbolicTensor/1/float, epsilon:float/0/float · returned SymbolicTensor · level recorded 2026-09-22
decode in 57 papers MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · b5e2ab32d7774a3c · report fixture: signature carry:tuple/1/ArrayImpl · returned tuple · level recorded 2026-09-22
greedy_decode in 9 papers MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · 4def9750b7938697 · report fixture: signature graph_indices:ArrayImpl/2/int, par:ArrayImpl/2/float · returned tuple · level recorded 2026-09-22
np_get_mis MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · a62b745a0dcdd413 · report fixture: signature graph_indices:ndarray/2/int, par:ndarray/2/float, diver_num:int/0/int, max_graph_size:int/0/int, max_num_edges:int/0/int · returned ndarray · level recorded 2026-09-22
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · 4bcb021dfa245389 · report fixture: signature carry:tuple/1/ArrayImpl · returned tuple · level recorded 2026-09-22
sample_with_log_prob MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · 760b81306eaa9b43 · report fixture: signature carry:tuple/1/ArrayImpl · returned tuple · level recorded 2026-09-22
sample_with_path MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · 131549b05f32ab16 · report fixture: signature carry:tuple/1/ArrayImpl · returned tuple · level recorded 2026-09-22
softmax_sample MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · 231026cfb60f11d3 · report fixture: signature jax_flag:ArrayImpl/1/bool, jax_solution:ArrayImpl/2/int, graph_indices:ArrayImpl/2/int, par:ArrayImpl/2/float, par_grad:ArrayImpl/2/float, rng_key:ArrayImpl/2/int, graph_size:int/0/int · returned tuple · level recorded 2026-09-22
softmax_sample_with_path MIS/solvers/intel_treesearch/NPHard/gcn/models.py ran · our draft was wrong MIT (permissive) · 110cc87d3e75606f · report fixture: signature jax_flag:ArrayImpl/1/bool, graph_indices:ArrayImpl/2/int, par:ArrayImpl/2/float, old_log_prob:ArrayImpl/2/float, par_grad:ArrayImpl/2/float, jax_path:ArrayImpl/2/int, old_reward:ArrayImpl/1/float, graph_size:int/0/int · returned tuple · level recorded 2026-09-22
Dense in 22 papers MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · fec438a4bb79bc5e · report
GCN_DEEP_DIVER_DIMES MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · fc2ba9d141d85b33 · report
GraphConvolution in 36 papers MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 7a01d3d524ba4bbe · report
Layer in 20 papers MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 8d9ecc956fcf5e40 · report
get_merged_aux_grad MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 7a81f93aab1b33f5 · report
get_merged_grad MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 81a3c043a4609a6e · report
get_merged_grad_with_path MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 5d34c2a954683213 · report
get_merged_sample MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 5b2fcfe0862b8fa4 · report
np_get_merged_grad MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · f33e88011484529a · report
np_get_merged_grad_ppo MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 8f730fab780fb806 · report
softmax_sample_log_prob MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · e5db5c5cacda2aca · report
sparse_dropout in 30 papers MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 295f9a13c181045b · report
tf_decode MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 0f22b7e497f6d57f · report
tf_par_grad MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 5991cfa2b123aef1 · report
tf_par_grad_ppo MIS/solvers/intel_treesearch/NPHard/gcn/models.py unverified MIT (permissive) · 3019512a49dd14af · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for DIMES (graph method: DIMES), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_policy_gradient entry · level 3 · ran · honoured contract · 59091c0c8ddde5fb241c7c7e59767c5aa604c50d9937096973f35b3e56c649cc

harvested Assembly for DIMES (graph method: DIMES). 27 bricks; individually on a fixture: 12 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 15 unverified. The assembly has not been run end-to-end.

  1. GCN_DEEP_DIVER_DIMES entry · level 0 · unverified · fc2ba9d141d85b33
  2. Dense model · level 0 · unverified · fec438a4bb79bc5e
  3. GraphConvolution model · level 0 · unverified · 7a01d3d524ba4bbe
  4. Model helper · level 1 · ran · bcdee00b1c1f4959
  5. tf_decode sampler · level 0 · unverified · 0f22b7e497f6d57f
  6. tf_par_grad update_rule · level 0 · unverified · 5991cfa2b123aef1
  7. tf_par_grad_ppo update_rule · level 0 · unverified · 3019512a49dd14af
  8. Layer helper · level 0 · unverified · 8d9ecc956fcf5e40
  9. apply_norm helper · level 1 · ran · our draft was wrong · 2e790af504140ec1
  10. dot helper · level 1 · ran · our draft was wrong · 57a66f8d8a42c2c2
  11. sparse_dropout helper · level 0 · unverified · 295f9a13c181045b
  12. np_get_mis helper · level 1 · ran · our draft was wrong · a62b745a0dcdd413
  13. np_get_merged_grad helper · level 0 · unverified · f33e88011484529a
  14. np_get_merged_grad_ppo helper · level 0 · unverified · 8f730fab780fb806
  15. get_layer_uid helper · level 1 · ran · honoured contract · b82968db452628fd
  16. greedy_decode sampler · level 1 · ran · our draft was wrong · 4def9750b7938697
  17. decode helper · level 1 · ran · our draft was wrong · b5e2ab32d7774a3c
  18. get_merged_aux_grad update_rule · level 0 · unverified · 7a81f93aab1b33f5
  19. get_merged_grad update_rule · level 0 · unverified · 81a3c043a4609a6e
  20. get_merged_grad_with_path helper · level 0 · unverified · 5d34c2a954683213
  21. get_merged_sample helper · level 0 · unverified · 5b2fcfe0862b8fa4
  22. sample helper · level 1 · ran · our draft was wrong · 4bcb021dfa245389
  23. sample_with_log_prob helper · level 1 · ran · our draft was wrong · 760b81306eaa9b43
  24. sample_with_path helper · level 1 · ran · our draft was wrong · 131549b05f32ab16
  25. softmax_sample sampler · level 1 · ran · our draft was wrong · 231026cfb60f11d3
  26. softmax_sample_log_prob sampler · level 0 · unverified · e5db5c5cacda2aca
  27. softmax_sample_with_path sampler · level 1 · ran · our draft was wrong · 110cc87d3e75606f

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="2210.04123") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Combinatorial OptimizationDeep Reinforcement LearningMeta-LearningTraveling Salesman Problem

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