Papers › A simple neural network module for relational reasoning

A simple neural network module for relational reasoning

5 Jun 2017NeurIPS 2017 12arXiv:1706.01427archive 2025-07-28

Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, Timothy Lillicrap

Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. We tested RN-augmented networks on three tasks: visual question answering using a challenging dataset called CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamic physical systems. Then, using a curated dataset called Sort-of-CLEVR we show that powerful convolutional networks do not have a general capacity to solve relational questions, but can gain this capacity when augmented with RNs. Our work shows how a deep learning architecture equipped with an RN module can implicitly discover and learn to reason about entities and their relations.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="1706.01427")

Code

Syntology Ran 3 of 7 code samples harvested from 5 repositories linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract.

By repository: community (archive-listed): 7 samples from 5 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

20 repositories listed; official and paper-mentioned ones first.

AndreaCossu/Relation-Network-PyTorch mentioned on GitHubpytorch report
IllgamhoDuck/ResTR mentioned on GitHubpytorch report
adriangoe/relational-networks-pytorch mentioned on GitHubpytorch report
cnichkawde/MatchingNetwork mentioned on GitHub report
fcorencoret/dynamic-rn mentioned on GitHubpytorch report
gngdb/relational mentioned on GitHubtorch report
jaehyunnn/RelationalNetwork_pytorch mentioned on GitHubpytorch report
kimhc6028/relational-networks mentioned on GitHubpytorch report
matwilso/relation-networks mentioned on GitHubtf report
mdda/relationships-from-entity-stream mentioned on GitHubpytorch report
mesnico/RelationNetworks-CLEVR mentioned on GitHubpytorch report
moduIo/Relation-Networks mentioned on GitHubtf report
nerdimite/relation-network mentioned on GitHubpytorch report
rishikmani/sort-of-clevr mentioned on GitHubtf report
rosinality/relation-networks-pytorch mentioned on GitHubpytorch report
siddk/relation-network mentioned on GitHubtf report
ttok0s7u2n5/ML2_proj mentioned on GitHubpytorch 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

7 samples harvested; 3 ran; 2 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
4unverified

Licence: 1 of the 7 samples is 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 5 repositories linked to this paper, official or community; each sample names its own and says which. “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.

center_generate kimhc6028/relational-networks/sort_of_clevr_generator.py community (archive-listed) ran · honoured contract BSD-3-Clause (permissive) · a0bf524db1b20389 · report
center_generate nerdimite/relation-network/data_generator.py community (archive-listed) ran · honoured contract no licence file found · pointer only · f44348c84f01ad92 · report
check_data_path clvrai/relation-network-tensorflow/trainer.py community (archive-listed) ran · violated contract MIT (permissive) · 3bd1e4d8ee61bea8 · report
append_embedding gngdb/relational/relational/core.py community (archive-listed) unverified Apache-2.0 (permissive) · 81bead1a816fe732 · report
cat gngdb/relational/relational/core.py community (archive-listed) unverified Apache-2.0 (permissive) · 7e9b59eed3132c73 · report
center_generate mdda/relationships-from-entity-stream/sort_of_clevr_generator.py community (archive-listed) unverified BSD-3-Clause (permissive) · 09f8f4cae4d23171 · report
prodpair gngdb/relational/relational/core.py community (archive-listed) unverified Apache-2.0 (permissive) · 50188557a08fb811 · report

Tasks

Image Retrieval with Multi-Modal QueryQuestion AnsweringRelational ReasoningVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval with Multi-Modal Query Fashion200k Relationship Recall@1 13 #5 of 8 Archive leaderboard report
Image Retrieval with Multi-Modal Query Fashion200k Relationship Recall@10 40.5 #5 of 8 Archive leaderboard report
Image Retrieval with Multi-Modal Query Fashion200k Relationship Recall@50 62.4 #5 of 8 Archive leaderboard report
Visual Question Answering (VQA) CLEVR CNN + LSTM + RN Accuracy 95.50 #14 of 15 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