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 repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2205.10128")

Code

Syntology Ran 1 of 4 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

DeepGraphLearning/GNN-QE officialmentioned in paperpytorchMIT 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; 1 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran
3unverified

Licence: 0 of the 4 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 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. “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.

computation_graph_layout DeepGraphLearning/GNN-QE/script/visualize.py official repository ran MIT (permissive) · 6b999fe6d54461d0 · report
detect_variables DeepGraphLearning/GNN-QE/gnnqe/util.py official repository unverified MIT (permissive) · eab8b6a6ced6d93e · report
get_root_logger DeepGraphLearning/GNN-QE/gnnqe/util.py official repository unverified MIT (permissive) · 70a68fd646c6e4a7 · report
get_topk_prediction DeepGraphLearning/GNN-QE/script/visualize.py official repository 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