CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

• URL: http://arxiv.org/abs/2412.16112v1
• Date: Fri, 20 Dec 2024 17:57:09 GMT
• Title: CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
• Authors: Songhua Liu, Zhenxiong Tan, Xinchao Wang,
• Abstract summary: We introduce a convolution-like local attention strategy termed CLEAR, which limits feature interactions to a local window around each query token. Experiments indicate that, by fine-tuning the attention layer on merely 10K self-generated samples for 10K iterations, we can effectively transfer knowledge from a pre-trained DiT to a student model with linear complexity.
• Score: 64.38715211969516
• License:
• Abstract: Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when generating high-resolution images. To address this issue, we aim at a linear attention mechanism in this paper that reduces the complexity of pre-trained DiTs to linear. We begin our exploration with a comprehensive summary of existing efficient attention mechanisms and identify four key factors crucial for successful linearization of pre-trained DiTs: locality, formulation consistency, high-rank attention maps, and feature integrity. Based on these insights, we introduce a convolution-like local attention strategy termed CLEAR, which limits feature interactions to a local window around each query token, and thus achieves linear complexity. Our experiments indicate that, by fine-tuning the attention layer on merely 10K self-generated samples for 10K iterations, we can effectively transfer knowledge from a pre-trained DiT to a student model with linear complexity, yielding results comparable to the teacher model. Simultaneously, it reduces attention computations by 99.5% and accelerates generation by 6.3 times for generating 8K-resolution images. Furthermore, we investigate favorable properties in the distilled attention layers, such as zero-shot generalization cross various models and plugins, and improved support for multi-GPU parallel inference. Models and codes are available here: https://github.com/Huage001/CLEAR.

Related papers

• ReGLA: Refining Gated Linear Attention [42.97193398172823]
  Linear attention has been designed to reduce the quadratic space-time complexity that is inherent in standard transformers. We developed a feature mapping function to address some crucial issues that previous suggestions overlooked. We also explored the saturation phenomenon of the gating mechanism and augmented it with a refining module.
  arXiv  Detail & Related papers  (2025-02-03T18:03:13Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• Learning Linear Attention in Polynomial Time [115.68795790532289]
  We provide the first results on learnability of single-layer Transformers with linear attention. We show that linear attention may be viewed as a linear predictor in a suitably defined RKHS. We show how to efficiently identify training datasets for which every empirical riskr is equivalent to the linear Transformer.
  arXiv  Detail & Related papers  (2024-10-14T02:41:01Z)
• EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models [29.57891007810509]
  Large Language Models (LLMs) have demonstrated outstanding performance across a variety of natural language processing tasks. We introduce EchoAtt, a novel framework aimed at optimizing transformer-based models by analyzing and leveraging the similarity of attention patterns across layers. Our best results with TinyLLaMA-1.1B demonstrate that EchoAtt improves inference speed by 15%, training speed by 25%, and reduces the number of parameters by approximately 4%, all while improving zero-shot performance.
  arXiv  Detail & Related papers  (2024-09-22T21:08:37Z)
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• LinFusion: 1 GPU, 1 Minute, 16K Image [71.44735417472043]
  We introduce a low-rank approximation of a wide spectrum of popular linear token mixers. We find that the distilled model, termed LinFusion, achieves performance on par with or superior to the original SD. Experiments on SD-v1.5, SD-v2.1, and SD-XL demonstrate that LinFusion enables satisfactory and efficient zero-shot cross-resolution generation.
  arXiv  Detail & Related papers  (2024-09-03T17:54:39Z)
• 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)
• Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers [42.93754828584075]
  We present a new Transformer architecture, Performer, based on Fast Attention Via Orthogonal Random features (FAVOR) Our mechanism scales linearly rather than quadratically in the number of tokens in the sequence, is characterized by sub-quadratic space complexity and does not incorporate any sparsity pattern priors. It provides strong theoretical guarantees: unbiased estimation of the attention matrix and uniform convergence.
  arXiv  Detail & Related papers  (2020-06-05T17:09:16Z)

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.