Block-Recurrent Transformers

• URL: http://arxiv.org/abs/2203.07852v1
• Date: Fri, 11 Mar 2022 23:44:33 GMT
• Title: Block-Recurrent Transformers
• Authors: DeLesley Hutchins, Imanol Schlag, Yuhuai Wu, Ethan Dyer, Behnam Neyshabur
• Abstract summary: We introduce the Block-Recurrent Transformer, which applies a transformer layer in a recurrent fashion along a sequence. Our recurrent cell operates on blocks of tokens rather than single tokens, and leverages parallel computation within a block in order to make efficient use of accelerator hardware.
• Score: 49.07682696216708
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce the Block-Recurrent Transformer, which applies a transformer layer in a recurrent fashion along a sequence, and has linear complexity with respect to sequence length. Our recurrent cell operates on blocks of tokens rather than single tokens, and leverages parallel computation within a block in order to make efficient use of accelerator hardware. The cell itself is strikingly simple. It is merely a transformer layer: it uses self-attention and cross-attention to efficiently compute a recurrent function over a large set of state vectors and tokens. Our design was inspired in part by LSTM cells, and it uses LSTM-style gates, but it scales the typical LSTM cell up by several orders of magnitude. Our implementation of recurrence has the same cost in both computation time and parameter count as a conventional transformer layer, but offers dramatically improved perplexity in language modeling tasks over very long sequences. Our model out-performs a long-range Transformer XL baseline by a wide margin, while running twice as fast. We demonstrate its effectiveness on PG19 (books), arXiv papers, and GitHub source code.

Related papers

• Parallelizing Linear Transformers with the Delta Rule over Sequence Length [49.88826673324244]
  This work describes a hardware-efficient algorithm for training linear transformers with the delta rule. We train a 1.3B model for 100B tokens and find that it outperforms recent linear-time baselines.
  arXiv  Detail & Related papers  (2024-06-10T17:24:42Z)
• MoEUT: Mixture-of-Experts Universal Transformers [75.96744719516813]
  Universal Transformers (UTs) have advantages over standard Transformers in learning compositional generalizations. Layer-sharing drastically reduces the parameter count compared to the non-shared model with the same dimensionality. No previous work has succeeded in proposing a shared-layer Transformer design that is competitive in parameter count-dominated tasks such as language modeling.
  arXiv  Detail & Related papers  (2024-05-25T03:24:32Z)
• Block-State Transformers [41.57016890030355]
  State space models (SSMs) have shown impressive results on tasks that require modeling long-range dependencies. We propose a hybrid layer named Block-State Transformer (BST) that internally combines an SSM sublayer for long-range contextualization. We show that our model outperforms similar Transformer-based architectures on language modeling perplexity and generalizes to longer sequences.
  arXiv  Detail & Related papers  (2023-06-15T22:48:08Z)
• Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator [24.690247474891958]
  Fourier Transformer is able to significantly reduce computational costs while retain the ability to inherit from various large pretrained models. Our model achieves state-of-the-art performances among all transformer-based models on the long-range modeling benchmark LRA. For generative seq-to-seq tasks including CNN/DailyMail and ELI5, by inheriting the BART weights our model outperforms the standard BART.
  arXiv  Detail & Related papers  (2023-05-24T12:33:06Z)
• Linearizing Transformer with Key-Value Memory Bank [54.83663647680612]
  We propose MemSizer, an approach to project the source sequence into lower dimension representation. MemSizer not only achieves the same linear time complexity but also enjoys efficient recurrent-style autoregressive generation. We demonstrate that MemSizer provides an improved tradeoff between efficiency and accuracy over the vanilla transformer.
  arXiv  Detail & Related papers  (2022-03-23T18:10:18Z)
• Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations [51.77000472945441]
  Long Short-Term Memory (LSTM) and Transformers are two popular neural architectures used for natural language processing tasks. In practice, it is often observed that Transformer models have better representation power than LSTM. We study such practical differences between LSTM and Transformer and propose an explanation based on their latent space decomposition patterns.
  arXiv  Detail & Related papers  (2021-12-16T19:56:44Z)
• Sparse is Enough in Scaling Transformers [12.561317511514469]
  Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We propose Scaling Transformers, a family of next generation Transformer models that use sparse layers to scale efficiently and perform unbatched decoding much faster than the standard Transformer.
  arXiv  Detail & Related papers  (2021-11-24T19:53:46Z)
• Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding [63.539333383965726]
  We propose a novel way to accelerate attention calculation for Transformers with relative positional encoding (RPE) Based upon the observation that relative positional encoding forms a Toeplitz matrix, we mathematically show that kernelized attention with RPE can be calculated efficiently using Fast Fourier Transform (FFT)
  arXiv  Detail & Related papers  (2021-06-23T17:51:26Z)
• FNet: Mixing Tokens with Fourier Transforms [0.578717214982749]
  We show that Transformer encoder architectures can be massively sped up with limited accuracy costs. We replace the self-attention sublayers with simple linear transformations that "mix" input tokens. The resulting model, which we name FNet, scales very efficiently to long inputs.
  arXiv  Detail & Related papers  (2021-05-09T03:32:48Z)
• Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention [22.228028613802174]
  Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, they are prohibitively slow for very long sequences. We make use of the associativity property of matrix products to reduce the complexity from $mathcalOleft(N2right)$ to $mathcalOleft(Nright)$, where $N$ is the sequence length. Our linear transformers achieve similar performance to vanilla transformers and they are up to 4000x faster on autoregressive prediction of very long sequences.
  arXiv  Detail & Related papers  (2020-06-29T17:55:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.