# Pretraining Without Attention

arXiv: https://arxiv.org/abs/2212.10544 · HTML: https://mlsanity.com/paper/2212.10544/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://mlsanity.com/paper/2008.07669/) (2020)
- [On the Parameterization and Initialization of Diagonal State Space Models](https://mlsanity.com/paper/2206.11893/) (2022)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Diagonal State Spaces are as Effective as Structured State Spaces](https://mlsanity.com/paper/2203.14343/) (2022)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [Long Range Language Modeling via Gated State Spaces](https://mlsanity.com/paper/2206.13947/) (2022)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [Assessing BERT's Syntactic Abilities](https://mlsanity.com/paper/1901.05287/) (2019)
- [Transformer Quality in Linear Time](https://mlsanity.com/paper/2202.10447/) (2022)
- [Mega: Moving Average Equipped Gated Attention](https://mlsanity.com/paper/2209.10655/) (2022)
- [It's Raw! Audio Generation with State-Space Models](https://mlsanity.com/paper/2202.09729/) (2022)
- [SCROLLS: Standardized CompaRison Over Long Language Sequences](https://mlsanity.com/paper/2201.03533/) (2022)

## Built on by (most cited first, 30 of 51)

- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Parallelizing Linear Transformers with the Delta Rule over Sequence Length](https://mlsanity.com/paper/2406.06484/) (2024)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [HGRN2: Gated Linear RNNs with State Expansion](https://mlsanity.com/paper/2404.07904/) (2024)
- [The Mamba in the Llama: Distilling and Accelerating Hybrid Models](https://mlsanity.com/paper/2408.15237/) (2024)
- [Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling](https://mlsanity.com/paper/2403.03234/) (2024)
- [Motion Mamba: Efficient and Long Sequence Motion Generation](https://mlsanity.com/paper/2403.07487/) (2024)
- [Hierarchically Gated Recurrent Neural Network for Sequence Modeling](https://mlsanity.com/paper/2311.04823/) (2023)
- [ZigMa: A DiT-style Zigzag Mamba Diffusion Model](https://mlsanity.com/paper/2403.13802/) (2024)
- [Diffusion Models Without Attention](https://mlsanity.com/paper/2311.18257/) (2023)
- [Theoretical Foundations of Deep Selective State-Space Models](https://mlsanity.com/paper/2402.19047/) (2024)
- [MambaByte: Token-free Selective State Space Model](https://mlsanity.com/paper/2401.13660/) (2024)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [Longhorn: State Space Models are Amortized Online Learners](https://mlsanity.com/paper/2407.14207/) (2024)
- [Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers](https://mlsanity.com/paper/2407.09941/) (2024)
- [MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection](https://mlsanity.com/paper/2403.19888/) (2024)
- [State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memory](https://mlsanity.com/paper/2309.13414/) (2023)
- [Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues](https://mlsanity.com/paper/2307.11888/) (2023)
- [FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores](https://mlsanity.com/paper/2311.05908/) (2023)
- [Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks](https://mlsanity.com/paper/2405.15731/) (2024)
- [Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT](https://mlsanity.com/paper/2402.07440/) (2024)
- [MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map](https://mlsanity.com/paper/2411.10741/) (2024)
- [SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces](https://mlsanity.com/paper/2403.07711/) (2024)
- [ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention](https://mlsanity.com/paper/2405.18425/) (2024)
- [Focus Your Attention (with Adaptive IIR Filters)](https://mlsanity.com/paper/2305.14952/) (2023)
- [Blockwise Parallel Transformer for Large Context Models](https://mlsanity.com/paper/2305.19370/) (2023)
- [Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation](https://mlsanity.com/paper/2405.16504/) (2024)
- [On the Long Range Abilities of Transformers](https://mlsanity.com/paper/2311.16620/) (2023)

## Abstract (arXiv)

Transformers have been essential to pretraining success in NLP. While other architectures have been used, downstream accuracy is either significantly worse, or requires attention layers to match standard benchmarks such as GLUE. This work explores pretraining without attention by using recent advances in sequence routing based on state-space models (SSMs). Our proposed model, Bidirectional Gated SSM (BiGS), combines SSM layers with a multiplicative gating architecture that has been effective in simplified sequence modeling architectures. The model learns static layers that do not consider pair-wise interactions. Even so, BiGS is able to match BERT pretraining accuracy on GLUE and can be extended to long-form pretraining of 4096 tokens without approximation. Analysis shows that while the models have similar average accuracy, the approach has different inductive biases than BERT in terms of interactions and syntactic representations. All models from this work are available at https://github.com/jxiw/BiGS.