SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.02096 · ICLR · 2022

Top-N: Equivariant set and graph generation without exchangeability

Clément Vignac, P. Frossard

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 2 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/2110.02096.json · badge: /api/ran/2110.02096.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
cvignac/top-n canonical (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran on a synthesized input
cvignac/top-n/set_generators.py
pointer only (licence: NONE) · get_code("d393f770567bf7dc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvignac/top-n 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.

generate_one_point Ran
ran; our contract draft was wrong, not the code
cvignac/top-n/utils/generate_synthetic_dataset.py
pointer only (licence: NONE) · get_code("f6994e39e5d1b6e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvignac/top-n 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.

generate_one_set Ran
ran; our contract draft was wrong, not the code
cvignac/top-n/utils/generate_synthetic_dataset.py
pointer only (licence: NONE) · get_code("65c04dff676a3a4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvignac/top-n 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.

round_n Ran
ran, honoured the contract we drafted
cvignac/top-n/set_generators.py
pointer only (licence: NONE) · get_code("e90190d109d8d3b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvignac/top-n 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.

SetGenerator Not yet run
unverified (harvested, no recorded run)
cvignac/top-n/set_generators.py
pointer only (licence: NONE) · get_code("b408f674f6e500b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvignac/top-n 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. No invocation recorded.

TopNGenerator Not yet run
unverified (harvested, no recorded run)
cvignac/top-n/set_generators.py
pointer only (licence: NONE) · get_code("536352c0a3fc8f2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvignac/top-n 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. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

This work addresses one-shot set and graph generation, and, more specifically, the parametrization of probabilistic decoders that map a vector-shaped prior to a distribution over sets or graphs. Sets and graphs are most commonly generated by first sampling points i.i.d. from a normal distribution, and then processing these points along with the prior vector using Transformer layers or Graph Neural Networks. This architecture is designed to generate exchangeable distributions, i.e., all permutations of the generated outputs are equally likely. We however show that it only optimizes a proxy to the evidence lower bound, which makes it hard to train. We then study equivariance in generative settings and show that nonexchangeable methods can still achieve permutation equivariance. Using this result, we introduce Top-n creation, a differentiable generation mechanism that uses the latent vector to select the most relevant points from a trainable reference set. Top-n can replace i.i.d. generation in any Variational Autoencoder or Generative Adversarial Network. Experimentally, our method outperforms i.i.d. generation by 15% at SetMNIST reconstruction, by 33% at object detection on CLEVR, generates sets that are 74% closer to the true distribution on a synthetic molecule-like dataset, and generates more valid molecules on QM9.

For agents

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

get_harvested_code_for_paper("2110.02096")
get_code_for_paper("2110.02096")
have("2110.02096")

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

curl https://syntology.ai/api/ran/2110.02096.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.02096.svg)](https://syntology.ai/paper/2110.02096)

Connect an agent — have() is free.