Pruning for Sparse Diffusion Models based on Gradient Flow

• URL: http://arxiv.org/abs/2501.09464v1
• Date: Thu, 16 Jan 2025 10:55:05 GMT
• Title: Pruning for Sparse Diffusion Models based on Gradient Flow
• Authors: Ben Wan, Tianyi Zheng, Zhaoyu Chen, Yuxiao Wang, Jia Wang,
• Abstract summary: Diffusion Models (DMs) have impressive capabilities among generation models, but are limited to slower inference speeds and higher computational costs. Previous works utilize one-shot structure pruning to derive lightweight DMs from pre-trained ones, but this approach often leads to a significant drop in generation quality. We propose a iterative pruning method based on gradient flow, including the gradient flow pruning process and the gradient flow pruning criterion.
• Score: 5.45577871017303
• License:
• Abstract: Diffusion Models (DMs) have impressive capabilities among generation models, but are limited to slower inference speeds and higher computational costs. Previous works utilize one-shot structure pruning to derive lightweight DMs from pre-trained ones, but this approach often leads to a significant drop in generation quality and may result in the removal of crucial weights. Thus we propose a iterative pruning method based on gradient flow, including the gradient flow pruning process and the gradient flow pruning criterion. We employ a progressive soft pruning strategy to maintain the continuity of the mask matrix and guide it along the gradient flow of the energy function based on the pruning criterion in sparse space, thereby avoiding the sudden information loss typically caused by one-shot pruning. Gradient-flow based criterion prune parameters whose removal increases the gradient norm of loss function and can enable fast convergence for a pruned model in iterative pruning stage. Our extensive experiments on widely used datasets demonstrate that our method achieves superior performance in efficiency and consistency with pre-trained models.

Related papers

• Optimization Insights into Deep Diagonal Linear Networks [10.395029724463672]
  We study the implicit regularization properties of the gradient flow "algorithm" for estimating the parameters of a deep diagonal neural network. Our main contribution is showing that this gradient flow induces a mirror flow dynamic on the model, meaning that it is biased towards a specific solution of the problem.
  arXiv  Detail & Related papers  (2024-12-21T20:23:47Z)
• Diffusion State-Guided Projected Gradient for Inverse Problems [82.24625224110099]
  We propose Diffusion State-Guided Projected Gradient (DiffStateGrad) for inverse problems. DiffStateGrad projects the measurement gradient onto a subspace that is a low-rank approximation of an intermediate state of the diffusion process. We highlight that DiffStateGrad improves the robustness of diffusion models in terms of the choice of measurement guidance step size and noise.
  arXiv  Detail & Related papers  (2024-10-04T14:26:54Z)
• FlowIE: Efficient Image Enhancement via Rectified Flow [71.6345505427213]
  FlowIE is a flow-based framework that estimates straight-line paths from an elementary distribution to high-quality images. Our contributions are rigorously validated through comprehensive experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-06-01T17:29:29Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• Minimizing Trajectory Curvature of ODE-based Generative Models [45.89620603363946]
  Recent generative models, such as diffusion models, rectified flows, and flow matching, define a generative process as a time reversal of a fixed forward process. We present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.
  arXiv  Detail & Related papers  (2023-01-27T21:52:03Z)
• Deep Equilibrium Optical Flow Estimation [80.80992684796566]
  Recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms. These RNNs impose large computation and memory overheads, and are not directly trained to model such stable estimation. We propose deep equilibrium (DEQ) flow estimators, an approach that directly solves for the flow as the infinite-level fixed point of an implicit layer.
  arXiv  Detail & Related papers  (2022-04-18T17:53:44Z)
• Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm [7.662952656290564]
  Various pruning approaches have been proposed to reduce the footprint requirements of Transformer-based language models. We show for the first time that reducing the risk of overfitting can help the effectiveness of pruning under the pretrain-and-finetune paradigm.
  arXiv  Detail & Related papers  (2021-10-15T16:42:56Z)
• Refining Deep Generative Models via Discriminator Gradient Flow [18.406499703293566]
  Discriminator Gradient flow (DGflow) is a new technique that improves generated samples via the gradient flow of entropy-regularized f-divergences. We show that DGflow leads to significant improvement in the quality of generated samples for a variety of generative models.
  arXiv  Detail & Related papers  (2020-12-01T19:10:15Z)
• A Gradient Flow Framework For Analyzing Network Pruning [11.247894240593693]
  Recent network pruning methods focus on pruning models early-on in training. We develop a general framework that uses gradient flow to unify importance measures through the norm of model parameters. We validate our claims on several VGG-13, MobileNet-V1, and ResNet-56 models trained on CIFAR-10/CIFAR-100.
  arXiv  Detail & Related papers  (2020-09-24T17:37:32Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.