Papers › Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

22 Oct 2020NeurIPS 2020 12arXiv:2010.11465archive 2025-07-28

Hongyu Ren, Jure Leskovec

One of the fundamental problems in Artificial Intelligence is to perform complex multi-hop logical reasoning over the facts captured by a knowledge graph (KG). This problem is challenging, because KGs can be massive and incomplete. Recent approaches embed KG entities in a low dimensional space and then use these embeddings to find the answer entities. However, it has been an outstanding challenge of how to handle arbitrary first-order logic (FOL) queries as present methods are limited to only a subset of FOL operators. In particular, the negation operator is not supported. An additional limitation of present methods is also that they cannot naturally model uncertainty. Here, we present BetaE, a probabilistic embedding framework for answering arbitrary FOL queries over KGs. BetaE is the first method that can handle a complete set of first-order logical operations: conjunction (∧), disjunction (∨), and negation (¬). A key insight of BetaE is to use probabilistic distributions with bounded support, specifically the Beta distribution, and embed queries/entities as distributions, which as a consequence allows us to also faithfully model uncertainty. Logical operations are performed in the embedding space by neural operators over the probabilistic embeddings. We demonstrate the performance of BetaE on answering arbitrary FOL queries on three large, incomplete KGs. While being more general, BetaE also increases relative performance by up to 25.4% over the current state-of-the-art KG reasoning methods that can only handle conjunctive queries without negation.

PaperPDFConference PDFCodeCode 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.

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

Code

Syntology 14 code samples harvested from 4 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 4 repositories, 9 ran (6 with no instrument failure; 3 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.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 9 samples that ran has no recorded date.

Blidge/KGReasoning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings (arXiv:2002.05969; that paper's own run record: 30 ran (of which 13 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 12 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
Jacfger/simple-stuffs mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
LHY-24/KG-Compilation mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
francoisluus/KGReasoning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Embedding Logical Queries on Knowledge Graphs (arXiv:1806.01445; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified) and Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings (arXiv:2002.05969; that paper's own run record: 30 ran (of which 13 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 12 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
hkust-knowcomp/efo-1-qa-benchmark mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs (arXiv:2109.08925; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
pminervini/kgreasoning mentioned on GitHubpytorchSyntology: not harvested report
snap-stanford/KGReasoning mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (3 instrument-failed) · 0 unverified report
uclnlp/cqd mentioned on GitHubpytorchSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
zhiweihu1103/qe-temp mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 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
3ran · our draft was wrong
4ran
5unverified

Licence: 2 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

Jacfger/simple-stuffs community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
BetaIntersection fol/estimator_beta.py ran · metamorphic tier: deterministic MIT (permissive) · 65d51f93f096ca1a · report fixture: signature alpha_embeddings:Tensor/2/float, beta_embeddings:Tensor/2/float · returned tuple · level recorded 2026-09-22
BetaProjection fol/estimator_beta.py ran · metamorphic tier: invariant MIT (permissive) · bc022c5d939d4dff · report fixture: signature e_embedding:Tensor/2/float, r_embedding:Tensor/2/float · returned Tensor · level recorded 2026-09-22
BetaEstimator fol/estimator_beta.py unverified MIT (permissive) · 83454511701e3bdd · report
LHY-24/KG-Compilation community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BetaIntersection src/models.py ran no licence file found · pointer only · 15f1515d95ce51d1 · report fixture: signature alpha_embeddings:Tensor/2/float, beta_embeddings:Tensor/2/float · returned tuple · level recorded 2026-09-24
snap-stanford/KGReasoning community (archive-listed) 5 samples, 5 ran (3 instrument-failed) · 0 unverified
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32
models.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · f44985272d18127a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
construct_graph in 9 papers create_queries.py ran MIT (permissive) · 75304c63d0f3ce0c · report fixture: signature base_path:str/0/str, indexified_files:list/1/str · returned tuple · level recorded 2026-09-24
eval_tuple in 5 papers util.py ran · our draft was wrong MIT (permissive) · 08bc9653c017dfb5 · report fixture: signature arg_return:str/0/str · returned tuple · level recorded 2026-09-22
list2tuple in 7 papers create_queries.py ran · our draft was wrong fingerprinted MIT (permissive) · 8c314b5b308ab1ad · report fixture: signature l:list/1/int · returned tuple · level recorded 2026-09-22
tuple2list in 5 papers create_queries.py ran · our draft was wrong fingerprinted MIT (permissive) · bbd072fbd86e1541 · report fixture: signature t:tuple/1/int · returned list · level recorded 2026-09-22
uclnlp/cqd community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
make_batches in 7 papers kbc/models.py ran · honoured contract fingerprinted MIT (permissive) · b602fff455d94358 · report fixture: signature size:int/0/int, batch_size:int/0/int · returned list · level recorded 2026-09-22
DynKBCSingleton kbc/models.py unverified MIT (permissive) · c1c62def2f1c5499 · report
KBCModel in 5 papers kbc/models.py unverified MIT (permissive) · a3016c183214fb5a · report
QuerDAG kbc/models.py unverified MIT (permissive) · ccc626ec21ffdcfb · report
Regularizer in 6 papers kbc/models.py unverified MIT (permissive) · dfce66d833684f59 · 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. 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for BETAE (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for BETAE (graph method: BETAE). 5 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. KBCModel entry · level 0 · unverified · a3016c183214fb5a
  2. DynKBCSingleton helper · level 0 · unverified · c1c62def2f1c5499
  3. QuerDAG helper · level 0 · unverified · ccc626ec21ffdcfb
  4. Regularizer helper · level 0 · unverified · dfce66d833684f59
  5. make_batches helper · level 1 · ran · honoured contract · b602fff455d94358

harvested Assembly for BETAE (graph method: BETAE). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. BetaIntersection entry · level 1 · ran · 15f1515d95ce51d1

harvested Assembly for BETAE (graph method: BETAE). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. BetaIntersection entry · level 1 · ran · 956e9a56d057daa5

harvested Assembly for BETAE (graph method: BETAE). 7 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. BetaEstimator entry · level 0 · unverified · 83454511701e3bdd
  2. AppFOQEstimator helper · level 0 · unverified · b8322293c1e3a4ac
  3. BetaIntersection model · level 1 · ran · 65d51f93f096ca1a
  4. BetaProjection model · level 1 · ran · bc022c5d939d4dff
  5. Regularizer helper · level 1 · ran · 4dd767dfdd3cd11d
  6. find_optimal_batch helper · level 1 · ran; the contract check could not run · d8b0a4e3912306de
  7. inclusion_sampling helper · level 1 · ran · our draft was wrong · c423c8497887b2c3

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="2010.11465") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Complex Query AnsweringKnowledge GraphsLogical ReasoningNegation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Complex Query Answering FB15k BetaE MRR 1p 0.651 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR 2i 0.558 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR 2p 0.257 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR 2u 0.401 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR 3i 0.665 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR 3p 0.247 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR ip 0.281 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR pi 0.439 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k BetaE MRR up 0.252 #6 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR 1p 0.39 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR 2i 0.288 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR 2p 0.109 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR 2u 0.124 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR 3i 0.425 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR 3p 0.1 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR ip 0.126 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR pi 0.224 #5 of 9 Archive leaderboard report
Complex Query Answering FB15k-237 BetaE MRR up 0.097 #5 of 9 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR 1p 0.53 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR 2i 0.376 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR 2p 0.13 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR 2u 0.122 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR 3i 0.475 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR 3p 0.114 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR ip 0.143 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR pi 0.241 #5 of 6 Archive leaderboard report
Complex Query Answering NELL-995 BetaE MRR up 0.085 #5 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.

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