Papers › Neural-Symbolic Models for Logical Queries on Knowledge Graphs

Neural-Symbolic Models for Logical Queries on Knowledge Graphs

16 May 2022ICML 2022 7arXiv:2205.10128archive 2025-07-28

Zhaocheng Zhu, Mikhail Galkin, Zuobai Zhang, Jian Tang

Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning. Traditional symbolic methods traverse a complete knowledge graph to extract the answers, which provides good interpretation for each step. Recent neural methods learn geometric embeddings for complex queries. These methods can generalize to incomplete knowledge graphs, but their reasoning process is hard to interpret. In this paper, we propose Graph Neural Network Query Executor (GNN-QE), a neural-symbolic model that enjoys the advantages of both worlds. GNN-QE decomposes a complex FOL query into relation projections and logical operations over fuzzy sets, which provides interpretability for intermediate variables. To reason about the missing links, GNN-QE adapts a graph neural network from knowledge graph completion to execute the relation projections, and models the logical operations with product fuzzy logic. Experiments on 3 datasets show that GNN-QE significantly improves over previous state-of-the-art models in answering FOL queries. Meanwhile, GNN-QE can predict the number of answers without explicit supervision, and provide visualizations for intermediate variables.

PaperPDFConference PDFCodeCode Syntology ran

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 4 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 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: 4 samples from 1 repository, 3 ran (1 with no instrument failure; 2 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DeepGraphLearning/GNN-QE officialmentioned in paperpytorchMITSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 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

4 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; 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
1ran
1unverified

Licence: 2 of the 4 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from DeepGraphLearning/GNN-QE. “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.

DeepGraphLearning/GNN-QE official repository 4 samples, 3 ran (2 instrument-failed) · 1 unverified
computation_graph_layout script/visualize.py ran MIT (permissive) · 6b999fe6d54461d0 · report fixture: signature depth:Tensor/1/int, left:Tensor/1/int, right:Tensor/1/int, width:int/0/int, height:int/0/int, vsep:int/0/int, hsep:int/0/int, pad:int/0/int · returned tuple · level recorded 2026-09-24
detect_variables in 8 papers gnnqe/util.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · eab8b6a6ced6d93e · report fixture: signature cfg_file:str/0/str · returned set · level recorded 2026-09-26
get_root_logger in 21 papers gnnqe/util.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 70a68fd646c6e4a7 · report fixture: returned RootLogger · level recorded 2026-09-26
get_topk_prediction script/visualize.py unverified MIT (permissive) · 0fdf31f60a2c67ea · report

Tasks

Complex Query AnsweringGraph Neural NetworkKnowledge Graphs

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Complex Query Answering FB15k GNN-QE MRR 1p 0.885 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR 2i 0.797 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR 2p 0.693 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR 2u 0.741 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR 3i 0.835 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR 3p 0.587 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR ip 0.704 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR pi 0.699 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k GNN-QE MRR up 0.610 #4 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR 1p 0.428 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR 2i 0.383 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR 2p 0.147 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR 2u 0.162 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR 3i 0.541 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR 3p 0.118 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR ip 0.189 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR pi 0.311 #3 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 GNN-QE MRR up 0.134 #3 of 9 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR 1p 0.533 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR 2i 0.424 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR 2p 0.189 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR 2u 0.159 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR 3i 0.525 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR 3p 0.149 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR ip 0.189 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR pi 0.308 #4 of 6 Archive leaderboard report
Complex Query Answering NELL-995 GNN-QE MRR up 0.126 #4 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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