Fast Multipole Attention: A Divide-and-Conquer Attention Mechanism for Long Sequences

• URL: http://arxiv.org/abs/2310.11960v3
• Date: Tue, 30 Jul 2024 15:02:51 GMT
• Title: Fast Multipole Attention: A Divide-and-Conquer Attention Mechanism for Long Sequences
• Authors: Yanming Kang, Giang Tran, Hans De Sterck,
• Abstract summary: We present Fast Multipole Attention, a new attention mechanism that uses a divide-and-conquer strategy to reduce the time and memory complexity of attention for sequences of length $n$. The hierarchical approach groups queries, keys, and values into $mathcalO( log n)$ levels of resolution, where groups at greater distances are larger in size and the weights to compute group quantities are learned. We find empirically that the Fast Multipole Transformer performs much better than other efficient transformers in terms of memory size and accuracy.
• Score: 1.5484595752241124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer-based models have achieved state-of-the-art performance in many areas. However, the quadratic complexity of self-attention with respect to the input length hinders the applicability of Transformer-based models to long sequences. To address this, we present Fast Multipole Attention, a new attention mechanism that uses a divide-and-conquer strategy to reduce the time and memory complexity of attention for sequences of length $n$ from $\mathcal{O}(n^2)$ to $\mathcal{O}(n \log n)$ or $O(n)$, while retaining a global receptive field. The hierarchical approach groups queries, keys, and values into $\mathcal{O}( \log n)$ levels of resolution, where groups at greater distances are increasingly larger in size and the weights to compute group quantities are learned. As such, the interaction between tokens far from each other is considered in lower resolution in an efficient hierarchical manner. The overall complexity of Fast Multipole Attention is $\mathcal{O}(n)$ or $\mathcal{O}(n \log n)$, depending on whether the queries are down-sampled or not. This multi-level divide-and-conquer strategy is inspired by fast summation methods from $n$-body physics and the Fast Multipole Method. We perform evaluation on autoregressive and bidirectional language modeling tasks and compare our Fast Multipole Attention model with other efficient attention variants on medium-size datasets. We find empirically that the Fast Multipole Transformer performs much better than other efficient transformers in terms of memory size and accuracy. The Fast Multipole Attention mechanism has the potential to empower large language models with much greater sequence lengths, taking the full context into account in an efficient, naturally hierarchical manner during training and when generating long sequences.

Related papers

• Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time [17.086679273053853]
  We show that a novel fast approximation method can calculate the gradients in almost linear time. By improving the efficiency of gradient, we hope that this work will facilitate more effective training and deployment of long-context language models.
  arXiv  Detail & Related papers  (2024-08-23T17:16:43Z)
• A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention [43.211427581302715]
  We propose Hierarchically Pruned Attention (HiP) to increase context length in large language models. HiP reduces the time complexity of the attention mechanism to $O(T log T)$ and the space complexity to $O(T)$, where $T$ is the sequence length. We show that HiP significantly reduces both prefill and decoding latencies, as well as memory usage, while maintaining high-quality generation with minimal degradation.
  arXiv  Detail & Related papers  (2024-06-14T08:32:45Z)
• HyperZ$\cdot$Z$\cdot$W Operator Connects Slow-Fast Networks for Full Context Interaction [0.0]
  Self-attention mechanism utilizes large implicit weight matrices, programmed through dot product-based activations with very few trainable parameters, to enable long sequence modeling. In this paper, we investigate the possibility of discarding residual learning by employing large implicit kernels to achieve full context interaction at each layer of the network. Our model incorporates several innovative components and exhibits excellent properties, such as introducing local feedback error for updating the slow network, stable zero-mean features, faster training convergence, and fewer model parameters.
  arXiv  Detail & Related papers  (2024-01-31T15:57:21Z)
• Efficient Long Sequence Modeling via State Space Augmented Transformer [92.74707853711374]
  We propose SPADE, short for $underlinetextbfS$tate sunderlinetextbfP$ace. We augment a SSM into the bottom layer of SPADE, and we employ efficient local attention methods for the other layers. Experimental results on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-12-15T20:51:27Z)
• Transformers Learn Shortcuts to Automata [52.015990420075944]
  We find that a low-depth Transformer can represent the computations of any finite-state automaton. We show that a Transformer with $O(log T)$ layers can exactly replicate the computation of an automaton on an input sequence of length $T$. We further investigate the brittleness of these solutions and propose potential mitigations.
  arXiv  Detail & Related papers  (2022-10-19T17:45:48Z)
• Fastformer: Additive Attention Can Be All You Need [51.79399904527525]
  We propose Fastformer, which is an efficient Transformer model based on additive attention. In Fastformer, instead of modeling the pair-wise interactions between tokens, we first use additive attention mechanism to model global contexts. In this way, Fastformer can achieve effective context modeling with linear complexity.
  arXiv  Detail & Related papers  (2021-08-20T09:44:44Z)
• Combiner: Full Attention Transformer with Sparse Computation Cost [142.10203598824964]
  We propose Combiner, which provides full attention capability in each attention head while maintaining low computation complexity. We show that most sparse attention patterns used in existing sparse transformers are able to inspire the design of such factorization for full attention. An experimental evaluation on both autoregressive and bidirectional sequence tasks demonstrates the effectiveness of this approach.
  arXiv  Detail & Related papers  (2021-07-12T22:43:11Z)
• 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)
• $O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers [71.31712741938837]
  We show that sparse Transformers with only $O(n)$ connections per attention layer can approximate the same function class as the dense model with $n2$ connections. We also present experiments comparing different patterns/levels of sparsity on standard NLP tasks.
  arXiv  Detail & Related papers  (2020-06-08T18:30:12Z)

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.