Papers › Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors

Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors

14 Apr 2023arXiv:2304.07063archive 2025-07-28

Hang Yin, ZiHao Wang, Yangqiu Song

Reasoning on knowledge graphs is a challenging task because it utilizes observed information to predict the missing one. Particularly, answering complex queries based on first-order logic is one of the crucial tasks to verify learning to reason abilities for generalization and composition. Recently, the prevailing method is query embedding which learns the embedding of a set of entities and treats logic operations as set operations and has shown great empirical success. Though there has been much research following the same formulation, many of its claims lack a formal and systematic inspection. In this paper, we rethink this formulation and justify many of the previous claims by characterizing the scope of queries investigated previously and precisely identifying the gap between its formulation and its goal, as well as providing complexity analysis for the currently investigated queries. Moreover, we develop a new dataset containing ten new types of queries with features that have never been considered and therefore can provide a thorough investigation of complex queries. Finally, we propose a new neural-symbolic method, Fuzzy Inference with Truth value (FIT), where we equip the neural link predictors with fuzzy logic theory to support end-to-end learning using complex queries with provable reasoning capability. Empirical results show that our method outperforms previous methods significantly in the new dataset and also surpasses previous methods in the existing dataset at the same time.

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 Fuzzy Inference with Truth value (FIT), generated from the paper text (not the authors' code), at level 2 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)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Fuzzy Inference with Truth value (FIT)') (how to connect); the free check have('2304.07063') needs no token.

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

Code

Syntology 41 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 21 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 41 samples from 1 repository, 20 ran (13 with no instrument failure; 7 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 20 samples that ran have no recorded date.

hkust-knowcomp/fit officialmentioned in papermentioned on GitHubpytorchMITSyntology: 41 samples, 20 ran (7 instrument-failed) · 21 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

41 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 21 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 · honoured contract
5ran · our draft was wrong
2ran; the contract check could not run
11ran
21unverified

Licence: 0 of the 41 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 hkust-knowcomp/fit. “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.

hkust-knowcomp/fit official repository 41 samples, 20 ran (7 instrument-failed) · 21 unverified
read_from_yaml QG_FIT.py ran · our draft was wrong MIT (permissive) · 84eb10126b44cd7c · report fixture: signature yaml_path:str/0/str · returned dict · level recorded, date not recorded
Config in 46 papers Neural_FIT.py ran MIT (permissive) · 2912753768ab645c · report fixture: returned dict · level recorded 2026-09-24
KGIndex Neural_FIT.py ran · metamorphic tier: deterministic MIT (permissive) · 9e89fde226cf805b · report fixture: signature name:str/0/str, eid:NoneType/0/? · returned NoneType · level recorded 2026-09-22
Kge_finetune Neural_FIT.py ran MIT (permissive) · 29357053d3c8e6cf · report fixture: signature rel_id:int/0/int, head_ent_vec:Tensor/1/float, train_mask:bool/0/bool · returned Tensor · level recorded 2026-09-24
KnowledgeGraphConfig Neural_FIT.py ran MIT (permissive) · e1a678914e17d9cc · report fixture: returned dict · level recorded 2026-09-24
RaggedBatch Neural_FIT.py ran · metamorphic tier: well formed fingerprinted MIT (permissive) · 2320379032a21fe0 · report fixture: signature padding_value:float/0/float · returned Tensor · level recorded 2026-09-22
_iter_triple_from_tsv Neural_FIT.py ran · our draft was wrong MIT (permissive) · c7e8b390d25b5532 · report fixture: signature triple_file:str/0/str, to_int:bool/0/bool, check_size:int/0/int · returned generator · level recorded 2026-09-22
align_entities_relations convert_beta_dataset.py ran MIT (permissive) · 2c5d6c341e63248e · report fixture: signature labeled_beta_type:list/1/str, beta_sample:list/1/Tensor · returned dict · level recorded 2026-09-24
check_candidate_set Neural_FIT.py ran · our draft was wrong MIT (permissive) · c94caad91983a47e · report fixture: signature candidate_set:dict/0/? · returned tuple · level recorded 2026-09-22
collect_matrix_scipy_sparse create_matrix.py ran MIT (permissive) · 330130ddfb49fc13 · report fixture: signature matrix_path:str/0/str · returned list · level recorded 2026-09-25
compute_batch_score_complex Neural_FIT.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · dfaa9a08584100be · report fixture: signature rel:Tensor/3/float, arg1:Tensor/3/float, arg2:Tensor/3/float, rank:int/0/int · returned Tensor · level recorded 2026-09-22
compute_batch_score_distmult compute_score.py ran fingerprinted MIT (permissive) · 1869521a4be75145 · report fixture: signature rel:Tensor/2/float, h_emb:Tensor/2/float, t_emb:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_batch_score_transe compute_score.py ran fingerprinted MIT (permissive) · 8c0698d90001cd35 · report fixture: signature rel:Tensor/2/float, h_emb:Tensor/2/float, t_emb:Tensor/2/float · returned Tensor · level recorded 2026-09-24
fixed_depth_nested_dict Neural_FIT.py ran · our draft was wrong MIT (permissive) · 7bd57dd5eaa81647 · report fixture: signature default_factory:callable/0/?, depth:int/0/int · returned defaultdict · level recorded 2026-09-22
iter_triple_from_tsv Neural_FIT.py ran · our draft was wrong MIT (permissive) · b1fab42528218ff3 · report fixture: signature triple_files:str/0/str, to_int:bool/0/bool, check_size:int/0/int · returned generator · level recorded 2026-09-22
load_beta_model QG_FIT.py ran · honoured contract MIT (permissive) · 25412604ebe7d821 · report fixture: signature checkpoint_path:str/0/str, model:callable/0/?, optimizer:SGD/0/? · returned tuple · level recorded, date not recorded
load_model in 479 papers QG_FIT.py ran · honoured contract MIT (permissive) · 4c08e440ba7f3e8c · report fixture: signature step:int/0/int, checkpoint_path:str/0/str, model:callable/0/?, opt:SGD/0/?, load_device:str/0/str · returned tuple · level recorded, date not recorded
log_add_metric evaluate_lmpnn.py ran MIT (permissive) · 8e7c46d561388d36 · report fixture: signature add_log:dict/0/?, mrr:float/0/float, h1:int/0/int, h3:int/0/int, h10:int/0/int, mul_mrr:float/0/float, h1_1:int/0/int, h3_3:int/0/int, h10_10:int/0/int · returned dict · level recorded 2026-09-24
ranking2metrics evaluate_lmpnn.py ran MIT (permissive) · e9bc5bf12edea40c · report fixture: signature ranking:Tensor/1/float, easy_ans:set/0/?, hard_ans:set/0/?, ranking_device:device/0/? · returned tuple · level recorded 2026-09-24
tensorize_batch_entities Neural_FIT.py ran; the contract check could not run (RAISES) MIT (permissive) · b048d0b5cfcddddc · report fixture: signature entities:list/1/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
FIT_finetune Neural_FIT.py unverified MIT (permissive) · 106410206f55ee55 · report
KnowledgeGraph Neural_FIT.py unverified MIT (permissive) · c7e631917f0831d7 · report
construct_matrix_dynamic Neural_FIT.py unverified MIT (permissive) · 58bd1c00d37189f3 · report
construct_matrix_list Neural_FIT.py unverified MIT (permissive) · e1824a035caa07b0 · report
csp_efo1 Neural_FIT.py unverified MIT (permissive) · de00fcf9dff8f944 · report
cut_node_sub_problem Neural_FIT.py unverified MIT (permissive) · b9fe352ddb40ce7c · report
evaluate_batch_joint evaluate_lmpnn.py unverified MIT (permissive) · 34cfe3992789f9f7 · report
extend_ans Neural_FIT.py unverified MIT (permissive) · 2d594b302a995572 · report
find_enumerate_node Neural_FIT.py unverified MIT (permissive) · 53b482ea547b3034 · report
find_leaf_node Neural_FIT.py unverified MIT (permissive) · c1c6d4c74680abee · report
kg_remove_node Neural_FIT.py unverified MIT (permissive) · d4fa4a2e520e91da · report
neural_cut_node_sub_problem Neural_FIT.py unverified MIT (permissive) · 9224a778f5fbd47f · report
neural_existential_update Neural_FIT.py unverified MIT (permissive) · 003464ef621fcac7 · report
neural_extend_ans Neural_FIT.py unverified MIT (permissive) · df6ae0aeda5453e6 · report
neural_solve_EFO1_X Neural_FIT.py unverified MIT (permissive) · 2868d57816b54ef1 · report
neural_solve_conjunctive Neural_FIT.py unverified MIT (permissive) · d9353c5d35da90dd · report
node_filter Neural_FIT.py unverified MIT (permissive) · 9c109521a0a3bf1c · report
node_pair_filtering Neural_FIT.py unverified MIT (permissive) · 4968b4d922dd7429 · report
solve_EFO1_new Neural_FIT.py unverified MIT (permissive) · 2a1fdf0490126a9e · report
solve_conjunctive Neural_FIT.py unverified MIT (permissive) · f408248313c609f9 · report
topology_filter Neural_FIT.py unverified MIT (permissive) · 95aa5762a066cf5b · 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 Fuzzy Inference with Truth value (FIT) (graph method: Fuzzy Inference with Truth value (FIT)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

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

  1. fuzzy_disjunction_over_enumeration entry · level 2 · ran · 58d72a7535223137c7bffa90c4e03d363dabcd99d4423132ee6a3672108db480

harvested Assembly for Fuzzy Inference with Truth value (FIT) (graph method: Fuzzy Inference with Truth value (FIT)). 31 bricks; individually on a fixture: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified. The assembly has not been run end-to-end.

  1. FIT_finetune entry · level 0 · unverified · 106410206f55ee55
  2. Kge_finetune model · level 1 · ran · 29357053d3c8e6cf
  3. KnowledgeGraph helper · level 0 · unverified · c7e631917f0831d7
  4. compute_batch_score_complex helper · level 1 · ran; the contract check could not run (RAISES) · dfaa9a08584100be
  5. neural_solve_EFO1_X model · level 0 · unverified · 2868d57816b54ef1
  6. solve_EFO1_new helper · level 0 · unverified · 2a1fdf0490126a9e
  7. KGIndex helper · level 1 · ran · 9e89fde226cf805b
  8. KnowledgeGraphConfig helper · level 1 · ran · e1a678914e17d9cc
  9. RaggedBatch helper · level 1 · ran · 2320379032a21fe0
  10. fixed_depth_nested_dict helper · level 1 · ran · our draft was wrong · 7bd57dd5eaa81647
  11. iter_triple_from_tsv helper · level 1 · ran · our draft was wrong · b1fab42528218ff3
  12. tensorize_batch_entities helper · level 1 · ran; the contract check could not run (RAISES) · b048d0b5cfcddddc
  13. neural_solve_conjunctive model · level 0 · unverified · d9353c5d35da90dd
  14. solve_conjunctive helper · level 0 · unverified · f408248313c609f9
  15. Config helper · level 1 · ran · 2912753768ab645c
  16. _iter_triple_from_tsv helper · level 1 · ran · our draft was wrong · c7e8b390d25b5532
  17. find_enumerate_node helper · level 0 · unverified · 53b482ea547b3034
  18. find_leaf_node helper · level 0 · unverified · c1c6d4c74680abee
  19. kg_remove_node helper · level 0 · unverified · d4fa4a2e520e91da
  20. neural_cut_node_sub_problem helper · level 0 · unverified · 9224a778f5fbd47f
  21. neural_extend_ans model · level 0 · unverified · df6ae0aeda5453e6
  22. cut_node_sub_problem helper · level 0 · unverified · b9fe352ddb40ce7c
  23. extend_ans helper · level 0 · unverified · 2d594b302a995572
  24. neural_existential_update model · level 0 · unverified · 003464ef621fcac7
  25. construct_matrix_dynamic helper · level 0 · unverified · 58bd1c00d37189f3
  26. csp_efo1 helper · level 0 · unverified · de00fcf9dff8f944
  27. node_pair_filtering helper · level 0 · unverified · 4968b4d922dd7429
  28. construct_matrix_list helper · level 0 · unverified · e1824a035caa07b0
  29. check_candidate_set helper · level 1 · ran · our draft was wrong · c94caad91983a47e
  30. node_filter helper · level 0 · unverified · 9c109521a0a3bf1c
  31. topology_filter helper · level 0 · unverified · 95aa5762a066cf5b

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="2304.07063") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Knowledge Graphs

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