# Compositional Attention Networks for Machine Reasoning

arXiv: https://arxiv.org/abs/1803.03067 · HTML: https://mlsanity.com/paper/1803.03067/

## Key facts

- Cited by 183 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2018.

## Built on by (most cited first, 30 of 183)

- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning](https://mlsanity.com/paper/2103.16002/) (2021)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals](https://mlsanity.com/paper/2101.03737/) (2021)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Benchmarking Spatial Relationships in Text-to-Image Generation](https://mlsanity.com/paper/2212.10015/) (2022)
- [Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning](https://mlsanity.com/paper/2212.00259/) (2022)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events](https://mlsanity.com/paper/2103.15538/) (2021)
- [Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem](https://mlsanity.com/paper/2411.00238/) (2024)
- [Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning](https://mlsanity.com/paper/2103.16564/) (2021)
- [Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training](https://mlsanity.com/paper/2106.13488/) (2021)
- [ComPhy: Compositional Physical Reasoning of Objects and Events from Videos](https://mlsanity.com/paper/2205.01089/) (2022)
- [3D Concept Learning and Reasoning from Multi-View Images](https://mlsanity.com/paper/2303.11327/) (2023)
- [Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text](https://mlsanity.com/paper/2307.07696/) (2023)
- [Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language](https://mlsanity.com/paper/2110.15358/) (2021)
- [EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering](https://mlsanity.com/paper/2312.12222/) (2023)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Modular Lifelong Reinforcement Learning via Neural Composition](https://mlsanity.com/paper/2207.00429/) (2022)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing](https://mlsanity.com/paper/2210.15889/) (2022)
- [PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning](https://mlsanity.com/paper/2112.05136/) (2021)
- [What's Left? Concept Grounding with Logic-Enhanced Foundation Models](https://mlsanity.com/paper/2310.16035/) (2023)
- [GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models](https://mlsanity.com/paper/2312.03543/) (2023)
- [Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA](https://mlsanity.com/paper/2103.09591/) (2021)

## Abstract (arXiv)

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.