Radial Networks: Dynamic Layer Routing for High-Performance Large Language Models

• URL: http://arxiv.org/abs/2404.04900v1
• Date: Sun, 7 Apr 2024 09:52:31 GMT
• Title: Radial Networks: Dynamic Layer Routing for High-Performance Large Language Models
• Authors: Jordan Dotzel, Yash Akhauri, Ahmed S. AbouElhamayed, Carly Jiang, Mohamed Abdelfattah, Zhiru Zhang,
• Abstract summary: Large language models (LLMs) often struggle with strict memory, latency, and power demands. Various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. We propose Radial Networks, which perform token-level routing between layers guided by a trained router module.
• Score: 9.637088945386227
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) often struggle with strict memory, latency, and power demands. To meet these demands, various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. These methods improve over static methods by exploiting the variance across individual inputs, which has steadily grown with the exponential increase in training data. Yet, the increasing depth within modern models, currently with hundreds of layers, has opened opportunities for dynamic layer sparsity, which skips the computation for entire layers. In this work, we explore the practicality of layer sparsity by profiling residual connections and establish the relationship between model depth and layer sparsity. For example, the residual blocks in the OPT-66B model have a median contribution of 5% to its output. We then take advantage of this dynamic sparsity and propose Radial Networks, which perform token-level routing between layers guided by a trained router module. These networks can be used in a post-training distillation from sequential networks or trained from scratch to co-learn the router and layer weights. They enable scaling to larger model sizes by decoupling the number of layers from the dynamic depth of the network, and their design allows for layer reuse. By varying the compute token by token, they reduce the overall resources needed for generating entire sequences. Overall, this leads to larger capacity networks with significantly lower compute and serving costs for large language models.

Related papers

• SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models [19.479746878680707]
  Layer pruning is a potent approach to reduce network size and improve computational efficiency. We propose a Similarity Guided fast Layer Partition pruning for compressing large deep models. Our method outperforms the state-of-the-art methods in both accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2024-10-14T04:01:08Z)
• Layer-wise Linear Mode Connectivity [52.6945036534469]
  Averaging neural network parameters is an intuitive method for the knowledge of two independent models. It is most prominently used in federated learning. We analyse the performance of the models that result from averaging single, or groups.
  arXiv  Detail & Related papers  (2023-07-13T09:39:10Z)
• ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models [9.96121040675476]
  This manuscript explores how properties of functions learned by neural networks of depth greater than two layers affect predictions. Our framework considers a family of networks of varying depths that all have the same capacity but different representation costs.
  arXiv  Detail & Related papers  (2023-05-24T22:10:12Z)
• The Underlying Correlated Dynamics in Neural Training [6.385006149689549]
  Training of neural networks is a computationally intensive task. We propose a model based on the correlation of the parameters' dynamics, which dramatically reduces the dimensionality. This representation enhances the understanding of the underlying training dynamics and can pave the way for designing better acceleration techniques.
  arXiv  Detail & Related papers  (2022-12-18T08:34:11Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Fully Dynamic Inference with Deep Neural Networks [19.833242253397206]
  Two compact networks, called Layer-Net (L-Net) and Channel-Net (C-Net), predict on a per-instance basis which layers or filters/channels are redundant and therefore should be skipped. On the CIFAR-10 dataset, LC-Net results in up to 11.9$times$ fewer floating-point operations (FLOPs) and up to 3.3% higher accuracy compared to other dynamic inference methods. On the ImageNet dataset, LC-Net achieves up to 1.4$times$ fewer FLOPs and up to 4.6% higher Top-1 accuracy than the other methods.
  arXiv  Detail & Related papers  (2020-07-29T23:17:48Z)
• DHP: Differentiable Meta Pruning via HyperNetworks [158.69345612783198]
  This paper introduces a differentiable pruning method via hypernetworks for automatic network pruning. Latent vectors control the output channels of the convolutional layers in the backbone network and act as a handle for the pruning of the layers. Experiments are conducted on various networks for image classification, single image super-resolution, and denoising.
  arXiv  Detail & Related papers  (2020-03-30T17:59:18Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)
• Convolutional Networks with Dense Connectivity [59.30634544498946]
  We introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks.
  arXiv  Detail & Related papers  (2020-01-08T06:54:53Z)

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.