Papers › Compositional Attention Networks for Machine Reasoning

Compositional Attention Networks for Machine Reasoning

8 Mar 2018ICLR 2018 1arXiv:1803.03067archive 2025-07-28

Drew A. Hudson, Christopher D. Manning

We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic black-box neural architectures towards a design that encourages both transparency and versatility. The model approaches problems by decomposing them into a series of attention-based reasoning steps, each performed by a novel recurrent Memory, Attention, and Composition (MAC) cell that maintains a separation between control and memory. By stringing the cells together and imposing structural constraints that regulate their interaction, MAC effectively learns to perform iterative reasoning processes that are directly inferred from the data in an end-to-end approach. We demonstrate the model's strength, robustness and interpretability on the challenging CLEVR dataset for visual reasoning, achieving a new state-of-the-art 98.9% accuracy, halving the error rate of the previous best model. More importantly, we show that the model is computationally-efficient and data-efficient, in particular requiring 5x less data than existing models to achieve strong results.

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="1803.03067")

Code

Syntology Ran 1 of 7 code samples harvested from 4 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 7 samples from 4 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

stanfordnlp/mac-network officialmentioned in papermentioned on GitHubtfApache-2.0 report
Glaciohound/VCML mentioned on GitHubpytorchMIT report
adlnlp/attention_vl mentioned on GitHubpytorch report
ceyzaguirre4/DACT-MAC mentioned on GitHubpytorchNOASSERTION report
ceyzaguirre4/mac-network-pytorch mentioned on GitHubpytorchMIT report
ivegner/Multi-Memory-MAC-Network mentioned on GitHubpytorch report
kakao/DAFT mentioned on GitHubpytorch report
ronilp/mac-network-pytorch-gqa mentioned on GitHubpytorch report
rosinality/mac-network-pytorch mentioned on GitHubpytorchMIT report
tohinz/pytorch-mac-network 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; 1 ran; 0 honoured the contract we drafted; 6 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.

1ran · our draft was wrong
6unverified

Licence: 0 of the 7 samples are 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 4 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.

linear ronilp/mac-network-pytorch-gqa/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 1bb3fb76f5e3c485 · report
collate_data ceyzaguirre4/mac-network-pytorch/dataset.py community (archive-listed) unverified MIT (permissive) · dc99e9ba297a65ae · report
collate_data rosinality/mac-network-pytorch/dataset.py community (archive-listed) unverified MIT (permissive) · 3489d58eb80cf2c6 · report
forward ceyzaguirre4/mac-network-pytorch/image_feature.py community (archive-listed) unverified MIT (permissive) · dbde19906ac732ed · report
load_MAC tohinz/pytorch-mac-network/code/mac.py community (archive-listed) unverified Apache-2.0 (permissive) · b66152de2215de9b · report
process_question ceyzaguirre4/mac-network-pytorch/preprocess.py community (archive-listed) unverified MIT (permissive) · 928267eac64ad657 · report
process_question rosinality/mac-network-pytorch/preprocess.py community (archive-listed) unverified MIT (permissive) · 6490066d39c2eafd · report

Tasks

Referring Expression ComprehensionVisual Question Answering (VQA)Visual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) CLEVR MAC Accuracy 98.9 #7 of 15 Archive leaderboard report
Visual Question Answering (VQA) CLEVR-Humans MAC Accuracy 81.5 #2 of 5 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

Interpretability

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