TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

• URL: http://arxiv.org/abs/2501.04765v2
• Date: Thu, 27 Mar 2025 14:42:53 GMT
• Title: TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training
• Authors: Felix Krause, Timy Phan, Ming Gui, Stefan Andreas Baumann, Vincent Tao Hu, Björn Ommer,
• Abstract summary: Diffusion models typically suffer from sample inefficiency and high training costs.<n>We show that TREAD reduces computational cost and simultaneously boosts model performance.<n>We achieve a competitive FID of 2.09 in a guided and 3.93 in an unguided setting.
• Score: 20.712053538676116
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and personalization were quickly adopted by the community. However, training these models in the first place remains very costly. While several recent approaches - including masking, distillation, and architectural modifications - have been proposed to improve training efficiency, each of these methods comes with a tradeoff: they achieve enhanced performance at the expense of increased computational cost or vice versa. In contrast, this work aims to improve training efficiency as well as generative performance at the same time through routes that act as a transport mechanism for randomly selected tokens from early layers to deeper layers of the model. Our method is not limited to the common transformer-based model - it can also be applied to state-space models and achieves this without architectural modifications or additional parameters. Finally, we show that TREAD reduces computational cost and simultaneously boosts model performance on the standard ImageNet-256 benchmark in class-conditional synthesis. Both of these benefits multiply to a convergence speedup of 14x at 400K training iterations compared to DiT and 37x compared to the best benchmark performance of DiT at 7M training iterations. Furthermore, we achieve a competitive FID of 2.09 in a guided and 3.93 in an unguided setting, which improves upon the DiT, without architectural changes.

Related papers

• Numerical Pruning for Efficient Autoregressive Models [87.56342118369123]
  This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and modules, respectively. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments.
  arXiv  Detail & Related papers  (2024-12-17T01:09:23Z)
• Truncated Consistency Models [57.50243901368328]
  Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints. We empirically find that this training paradigm limits the one-step generation performance of consistency models. We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
  arXiv  Detail & Related papers  (2024-10-18T22:38:08Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• KIND: Knowledge Integration and Diversion in Diffusion Models [40.442303050947395]
  We introduce textbfKIND, which performs textbfKnowledge textbfINtegration and textbfDiversion in diffusion models. KIND redefines traditional pre-training methods by adjusting training objectives from maximizing model performance on current tasks to condensing transferable common knowledge. Results indicate that KIND achieves state-of-the-art performance compared to other PEFT and learngene methods.
  arXiv  Detail & Related papers  (2024-08-14T07:22:28Z)
• Diffusion Models as Optimizers for Efficient Planning in Offline RL [47.0835433289033]
  Diffusion models have shown strong competitiveness in offline reinforcement learning tasks. We propose a faster autoregressive model to handle the generation of feasible trajectories. This allows us to achieve more efficient planning without sacrificing capability.
  arXiv  Detail & Related papers  (2024-07-23T03:00:01Z)
• Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training [32.154166415680066]
  Methods like distillation, compression or quantization help leverage the highly performant large models to induce smaller performant ones. This paper explores the hypothesis that a single training run can simultaneously train a larger model for performance and derive a smaller model for deployment.
  arXiv  Detail & Related papers  (2024-02-07T17:07:41Z)
• Time-, Memory- and Parameter-Efficient Visual Adaptation [75.28557015773217]
  We propose an adaptation method which does not backpropagate gradients through the backbone. We achieve this by designing a lightweight network in parallel that operates on features from the frozen, pretrained backbone.
  arXiv  Detail & Related papers  (2024-02-05T10:55:47Z)
• A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization [54.113083217869516]
  In this work, we first explore the computational redundancy part of the network. We then prune the redundancy blocks of the model and maintain the network performance. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part.
  arXiv  Detail & Related papers  (2023-12-24T15:37:47Z)
• ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models [59.90959789767886]
  We show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions. By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$times$64 and LSUN Cat 256$times$256 datasets.
  arXiv  Detail & Related papers  (2023-11-23T16:49:06Z)
• Maestro: Uncovering Low-Rank Structures via Trainable Decomposition [15.254107731735553]
  Deep Neural Networks (DNNs) have been a large driver for AI breakthroughs in recent years. They have been getting increasingly large as they become more accurate and safe. This means that their training becomes increasingly costly and time-consuming. We propose Maestro, a framework for trainable low-rank layers.
  arXiv  Detail & Related papers  (2023-08-28T23:08:15Z)
• Towards Compute-Optimal Transfer Learning [82.88829463290041]
  We argue that zero-shot structured pruning of pretrained models allows them to increase compute efficiency with minimal reduction in performance. Our results show that pruning convolutional filters of pretrained models can lead to more than 20% performance improvement in low computational regimes.
  arXiv  Detail & Related papers  (2023-04-25T21:49:09Z)
• Online Convolutional Re-parameterization [51.97831675242173]
  We present online convolutional re- parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks.
  arXiv  Detail & Related papers  (2022-04-02T09:50:19Z)
• Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training [8.411385346896413]
  We focus on improving the practical efficiency of the state-of-the-art EfficientNet models on a new class of accelerator, the Graphcore IPU. We do this by extending this family of models in the following ways: (i) generalising depthwise convolutions to group convolutions; (ii) adding proxy-normalized activations to match batch normalization performance with batch-independent statistics; and (iii) reducing compute by lowering the training resolution and inexpensively fine-tuning at higher resolution.
  arXiv  Detail & Related papers  (2021-06-07T14:10:52Z)
• Top-KAST: Top-K Always Sparse Training [50.05611544535801]
  We propose Top-KAST, a method that preserves constant sparsity throughout training. We show that it performs comparably to or better than previous works when training models on the established ImageNet benchmark. In addition to our ImageNet results, we also demonstrate our approach in the domain of language modeling.
  arXiv  Detail & Related papers  (2021-06-07T11:13:05Z)
• Transfer Learning Between Different Architectures Via Weights Injection [0.0]
  This work presents a naive algorithm for parameter transfer between different architectures with a computationally cheap injection technique. The primary objective is to speed up the training of neural networks from scratch.
  arXiv  Detail & Related papers  (2021-01-07T20:42:35Z)
• Towards Practical Lipreading with Distilled and Efficient Models [57.41253104365274]
  Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. There is still a significant gap between the current methodologies and the requirements for an effective deployment of lipreading in practical scenarios. We propose a series of innovations that significantly bridge that gap: first, we raise the state-of-the-art performance by a wide margin on LRW and LRW-1000 to 88.5% and 46.6%, respectively using self-distillation.
  arXiv  Detail & Related papers  (2020-07-13T16:56:27Z)

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.