Papers › Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

13 Jun 2021NeurIPS 2021 12arXiv:2106.06935archive 2025-07-28

Zhaocheng Zhu, Zuobai Zhang, Louis-Pascal Xhonneux, Jian Tang

Link prediction is a very fundamental task on graphs. Inspired by traditional path-based methods, in this paper we propose a general and flexible representation learning framework based on paths for link prediction. Specifically, we define the representation of a pair of nodes as the generalized sum of all path representations, with each path representation as the generalized product of the edge representations in the path. Motivated by the Bellman-Ford algorithm for solving the shortest path problem, we show that the proposed path formulation can be efficiently solved by the generalized Bellman-Ford algorithm. To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm. The NBFNet parameterizes the generalized Bellman-Ford algorithm with 3 neural components, namely INDICATOR, MESSAGE and AGGREGATE functions, which corresponds to the boundary condition, multiplication operator, and summation operator respectively. The NBFNet is very general, covers many traditional path-based methods, and can be applied to both homogeneous graphs and multi-relational graphs (e.g., knowledge graphs) in both transductive and inductive settings. Experiments on both homogeneous graphs and knowledge graphs show that the proposed NBFNet outperforms existing methods by a large margin in both transductive and inductive settings, achieving new state-of-the-art results.

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.

Syntology holds a reference implementation of Neural Bellman-Ford Network (NBFNet), 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='Neural Bellman-Ford Network (NBFNet)') (how to connect); the free check have('2106.06935') needs no token.

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

Code

Syntology 15 code samples harvested from 3 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 11 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed); community: 2 samples from 1 repository, 2 ran (0 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. 2 of the 12 samples that ran have no recorded date.

DeepGraphLearning/NBFNet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
fs302/EasyLink mentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified report
fs302/EasyLink mentioned on GitHubpytorchSyntology: 11 samples, 8 ran (0 instrument-failed) · 3 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 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.

4ran · our draft was wrong
8ran
3unverified

Licence: 2 of the 15 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 3 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.

DeepGraphLearning/NBFNet official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
detect_variables in 8 papers nbfnet/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 nbfnet/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
fs302/EasyLink community (archive-listed) 11 samples, 8 ran (0 instrument-failed) · 3 unverified
drnl_node_labeling easylink/common/seal_utils.py ran Apache-2.0 (permissive) · 2aad32b3b74abec9 · report fixture: signature adj:csr_matrix/2/float, src:int/0/int, dst:int/0/int · returned Tensor · level recorded 2026-09-24
evaluate_auc in 5 papers easylink/common/eval_utils.py ran Apache-2.0 (permissive) · a27462150ae41053 · report fixture: signature val_pred:ndarray/1/float, val_true:ndarray/1/int, test_pred:ndarray/1/float, test_true:ndarray/1/int · returned dict · level recorded 2026-09-24
evaluate_hits easylink/common/eval_utils.py ran Apache-2.0 (permissive) · e18c89b0a6b12062 · report fixture: signature evaluator:MockEvaluator/0/?, pos_val_pred:Tensor/1/float, neg_val_pred:Tensor/1/float, pos_test_pred:Tensor/1/float, neg_test_pred:Tensor/1/float · returned dict · level recorded 2026-09-24
extract_enclosing_subgraphs easylink/common/seal_utils.py ran Apache-2.0 (permissive) · 9df677a47f14ae09 · report fixture: signature link_index:Tensor/2/int, A:csr_matrix/2/int, x:Tensor/2/float, y:int/0/int, num_hops:int/0/int, node_label:str/0/str, max_nodes_per_hop:int/0/int · returned list · level recorded 2026-09-24
get_pos_neg_edges easylink/common/seal_utils.py ran Apache-2.0 (permissive) · fcaa1fff9342a53d · report fixture: signature edge_index:Tensor/2/int, num_nodes:int/0/int, neg_edge_index:NoneType/0/?, neg_sample_rate:int/0/int, percent:int/0/int · returned tuple · level recorded 2026-09-24
load_basic_network easylink/common/data_utils.py ran Apache-2.0 (permissive) · 00fab49fcf976780 · report fixture: signature file_path:str/0/str, graph_type:str/0/str · returned Graph · level recorded 2026-09-24
sparse_to_tuple in 22 papers easylink/common/data_utils.py ran Apache-2.0 (permissive) · 4ada13b9756aa281 · report fixture: signature sparse_mx:csr_matrix/2/float · returned tuple · level recorded 2026-09-24
train_test_split in 23 papers easylink/common/data_utils.py ran Apache-2.0 (permissive) · f6e29676a8cc379b · report fixture: signature nx_adj:csr_matrix/2/float, test_frac:float/0/float, val_frac:float/0/float, pos_neg_ratio:float/0/float · returned tuple · level recorded 2026-09-24
adamic_adar easylink/model/heuristic_similarity.py unverified Apache-2.0 (permissive) · cb453fdedf2fff1d · report
common_neighbors easylink/model/heuristic_similarity.py unverified Apache-2.0 (permissive) · 5f30e06f74863f65 · report
resource_allocation easylink/model/heuristic_similarity.py unverified Apache-2.0 (permissive) · 213410a6123cfb65 · report
KiddoZhu/NBFNet-PyG community 2 samples, 2 ran (2 instrument-failed) · 0 unverified
index_to_mask in 25 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
nbfnet/models.py ran · our draft was wrong MIT (permissive) · 9664f4b5c60ab1bf · report fixture: signature index:Tensor/1/int, size:int/0/int · returned Tensor · level recorded, date not recorded
size_to_index nbfnet/models.py ran · our draft was wrong MIT (permissive) · 4ddf5f547371a7f7 · report fixture: signature size:Tensor/1/int · returned Tensor · level recorded, date not recorded

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. 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.

1 assembly on this paper: 0 harvested, 1 generated.

generated Assembly for Neural Bellman-Ford Network (NBFNet) (graph method: Neural Bellman-Ford Network (NBFNet)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 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. nbfnet_bellman_ford_iteration entry · level 3 · ran; the contract check could not run · 3b25c98b0753e2b0eb116abee2d033c6bf1031fe427765499967d077be9b9eaa

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="2106.06935") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph Neural NetworkInductive Relation PredictionKnowledge Graph CompletionLink PredictionLink Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction Citeseer NBFNet AP 93.6% #9 of 13 Archive leaderboard report
Link Prediction Citeseer NBFNet AUC 92.3% #9 of 13 Archive leaderboard report
Link Prediction Cora NBFNet AP 96.2% #3 of 13 Archive leaderboard report
Link Prediction Cora NBFNet AUC 95.6% #3 of 13 Archive leaderboard report
Link Prediction FB15k-237 NBFNet Hits@1 0.321 #1 of 75 Archive leaderboard report
Link Prediction FB15k-237 NBFNet Hits@10 0.599 #1 of 75 Archive leaderboard report
Link Prediction FB15k-237 NBFNet Hits@3 0.454 #1 of 75 Archive leaderboard report
Link Prediction FB15k-237 NBFNet MR 114 #1 of 75 Archive leaderboard report
Link Prediction FB15k-237 NBFNet MRR 0.415 #1 of 75 Archive leaderboard report
Link Prediction Pubmed NBFNet AP 98.2% #3 of 13 Archive leaderboard report
Link Prediction Pubmed NBFNet AUC 98.3% #3 of 13 Archive leaderboard report
Link Prediction WN18RR NBFNet Hits@1 0.497 #12 of 75 Archive leaderboard report
Link Prediction WN18RR NBFNet Hits@10 0.666 #12 of 75 Archive leaderboard report
Link Prediction WN18RR NBFNet Hits@3 0.573 #12 of 75 Archive leaderboard report
Link Prediction WN18RR NBFNet MR 636 #12 of 75 Archive leaderboard report
Link Prediction WN18RR NBFNet MRR 0.551 #12 of 75 Archive leaderboard report
Link Prediction YAGO3-10 NBFNet Hits@1 0.480 #8 of 18 Archive leaderboard report
Link Prediction YAGO3-10 NBFNet Hits@10 0.708 #8 of 18 Archive leaderboard report
Link Prediction YAGO3-10 NBFNet Hits@3 0.612 #8 of 18 Archive leaderboard report
Link Prediction YAGO3-10 NBFNet MRR 0.563 #8 of 18 Archive leaderboard report
Link Property Prediction ogbl-biokg NBFNet Ext. data No #10 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg NBFNet Number of params 734,209 #10 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg NBFNet Test MRR 0.8317 #10 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg NBFNet Validation MRR 0.8318 #10 of 16 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