SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.16103 · NeurIPS · 2021

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

Pan Li, Muhan Zhang, Yinglong Xia, Kai Wang, Long Jin

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2010.16103.json · badge: /api/ran/2010.16103.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
facebookresearch/SEAL_OGB canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
dmlc/dgl community
Papers with Code archive
0 ran · 2 no recorded run
facebookresearch/seal_ogb reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
FunctionStatusWhere it lives
drnl_node_labeling Ran
ran on a synthesized input
facebookresearch/SEAL_OGB/utils.py
pointer only (licence: MIT) · get_code("7850cdbb204f1583")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/SEAL_OGB, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

k_hop_subgraph Ran
ran; our contract draft was wrong, not the code
facebookresearch/SEAL_OGB/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from arianemarandon/linkpredconf, is pointer only (licence: NONE) · get_code("c14b46da419ba958")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from arianemarandon/linkpredconf, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

neighbors Ran
ran; our contract draft was wrong, not the code
facebookresearch/SEAL_OGB/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from arianemarandon/linkpredconf, is pointer only (licence: NONE) · get_code("fe208db98a8e47fb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from arianemarandon/linkpredconf, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

check_pytorch Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/label_informativeness.py
code served (permissive licence) · get_code("e053d92230933aac")
How it ran

no invocation recorded.

edge_label_informativeness Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/label_informativeness.py
code served (permissive licence) · get_code("b47785e45de29a98")
How it ran

no invocation recorded.

evaluate_hits Not yet run
unverified (harvested, no recorded run)
facebookresearch/seal_ogb/seal_link_pred.py
code served (permissive licence) · get_code("ab8f4436bf3f8fc9")
How it ran

no invocation recorded.

evaluate_mrr Not yet run
unverified (harvested, no recorded run)
facebookresearch/seal_ogb/seal_link_pred.py
code served (permissive licence) · get_code("c0086a518214536a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
neighbors 2 other papers
1 dated earlier, 1 later
2005.00687 (2020-05)
Open Graph Benchmark: Datasets for Machine Learning on Graphs
2306.14693 (2023-06)
Conformal link prediction for false discovery rate control
evaluate_hits 1 other paper
1 dated earlier
1802.09691 (2018-02)
Link Prediction Based on Graph Neural Networks
evaluate_mrr 1 other paper
1 dated earlier
1802.09691 (2018-02)
Link Prediction Based on Graph Neural Networks
k_hop_subgraph 1 other paper
1 later
2306.14693 (2023-06)
Conformal link prediction for false discovery rate control

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we provide a theory of using graph neural networks (GNNs) for multinode representation learning (where we are interested in learning a representation for a set of more than one node, such as link). We know that GNN is designed to learn single-node representations. When we want to learn a node set representation involving multiple nodes, a common practice in previous works is to directly aggregate the single-node representations obtained by a GNN into a joint node set representation. In this paper, we show a fundamental constraint of such an approach, namely the inability to capture the dependence between nodes in the node set, and argue that directly aggregating individual node representations does not lead to an effective joint representation for multiple nodes. Then, we notice that a few previous successful works for multi-node representation learning, including SEAL, Distance Encoding, and ID-GNN, all used node labeling. These methods first label nodes in the graph according to their relationships with the target node set before applying a GNN. Then, the node representations obtained in the labeled graph are aggregated into a node set representation. By investigating their inner mechanisms, we unify these node labeling techniques into a single and most general form-labeling trick. We prove that with labeling trick a sufficiently expressive GNN learns the most expressive node set representations, thus in principle solves any joint learning tasks over node sets. Experiments on one important two-node representation learning task, link prediction, verified our theory. Our work explains the superior performance of previous node-labeling-based methods, and establishes a theoretical foundation of using GNNs for multi-node representation learning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.16103")
get_code_for_paper("2010.16103")
have("2010.16103")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2010.16103.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2010.16103.svg)](https://syntology.ai/paper/2010.16103)

Connect an agent — have() is free.