# Product Interaction: An Algebraic Formalism for Deep Learning Architectures

arXiv: https://arxiv.org/abs/2602.02573 · HTML: https://mlsanity.com/paper/2602.02573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds](https://mlsanity.com/paper/1802.08219/) (2018)
- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data](https://mlsanity.com/paper/1807.02547/) (2018)
- [Harmonic Networks: Deep Translation and Rotation Equivariance](https://mlsanity.com/paper/1612.04642/) (2016)
- [Gauge Equivariant Convolutional Networks and the Icosahedral CNN](https://mlsanity.com/paper/1902.04615/) (2019)
- [A General Theory of Equivariant CNNs on Homogeneous Spaces](https://mlsanity.com/paper/1811.02017/) (2018)
- [Pay Less Attention with Lightweight and Dynamic Convolutions](https://mlsanity.com/paper/1901.10430/) (2019)
- [Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network](https://mlsanity.com/paper/1806.09231/) (2018)
- [Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View](https://mlsanity.com/paper/1906.02762/) (2019)
- [LieTransformer: Equivariant self-attention for Lie Groups](https://mlsanity.com/paper/2012.10885/) (2020)
- [Position: Categorical Deep Learning is an Algebraic Theory of All Architectures](https://mlsanity.com/paper/2402.15332/) (2024)
- [Tensor Product Attention Is All You Need](https://mlsanity.com/paper/2501.06425/) (2025)
- [X-volution: On the unification of convolution and self-attention](https://mlsanity.com/paper/2106.02253/) (2021)
- [Block-Biased Mamba for Long-Range Sequence Processing](https://mlsanity.com/paper/2505.09022/) (2025)

## Abstract (arXiv)

Modern neural architectures are largely developed as distinct empirical constructions, despite recurring principles across convolutional, attention, state-space, and equivariant models. We introduce Product Interactions, an algebraic formalism that unifies these architectures under a common construction principle and turns their design into a systematic procedure. The core shift is representing data as algebraic elements and treating multiplication, rather than linear transformation alone, as a primitive architectural operation. Architectures are generated by composing multiplication operators, with input dependence organized by self-interaction order. Within this formalism, we derive convolutional and equivariant networks as symmetry-constrained first-order product interactions, recover Mamba from state-space models as an increase in self-interaction order from one to three, and establish attention as a third-order interaction from composing the same operator. Equivariance is incorporated by constraining the algebraic product via symmetry: translation equivariance yields convolution, while SO(3)-compatibility produces the Clebsch--Gordan product and tensor-field interactions. This perspective recasts architecture design as an algebraic construction problem: the choice of algebra defines admissible interactions, symmetry constrains their structure, and composition generates higher-order architectures. The framework is thus generative. Following these principles, we construct a simplified-algebra dynamical layer that improves both accuracy and throughput over Mamba on CIFAR-10. Experiments show that interaction order affects accuracy non-monotonically and symmetry constraints boost learnability. Product Interactions provides a mathematical methodology for analyzing existing architectures and systematically designing new ones.