Network pruning focuses on algorithms that aim to reduce a given model's computational cost by removing a subset of its parameters while having minimal impact on performance. Throughout the last decade, the most widely used pruning paradigm has been pruning and re-training, which nowadays is inconvenient due to the vast amount of pre-trained models, which are, in any case, too expensive to re-train. In this paper, we exploit functional information from dense pre-trained models, i.e., their input activations, to obtain sparse models that maximize the activations' alignment with respect to their corresponding dense models. Hence, we propose \textbf{NeuroAl}, a \emph{top-up} algorithm that can be used on top of any given pruning algorithm for LLMs, which modifies the block-wise and row-wise sparsity, exploiting information from both the dense model and its sparse version to maximize the \emph{neuron alignment} among activations. Different from existing methods, our approach adaptively selects the best hyperparameters for the block-wise and row-wise sparsity ratios w.r.t. the model and the desired sparsity, and requires \emph{no re-training}. We test our method over $\sim$300 test cases with four LLM families, three sparsity ratios, and ten language tasks (three language modeling and seven zero-shot datasets), showing how it consistently outperforms the latest state-of-the-art methods in terms of performance-runtime trade-off. The code is available at \href{https://github.com/eliacunegatti/NeuroAL}{https://github.com/eliacunegatti/NeuroAL}.
GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
Department of Computing, The Hong Kong Polytechnic University, Hong Kong（香港理工大学计算机系）；School of Artificial Intelligence and Data Science, IIT Jodhpur（IIT朱罗浦人工智能与数据科学学院）
DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging
Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA（语言与语音处理中心，约翰霍普金斯大学，巴尔的摩，MD，美国）；Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA（人工智能语言技术卓越中心，约翰霍普金斯大学，巴尔的摩，MD，美国）
Auto-regressive large language models such as GPT-3 require enormous computational resources to use. Traditionally, structured pruning methods are employed to reduce resource usage. However, their application to and efficacy for generative language models is heavily under-explored. In this paper we conduct an comprehensive evaluation of common structured pruning methods, including magnitude, random, and movement pruning on the feed-forward layers in GPT-type models. Unexpectedly, random pruning results in performance that is comparable to the best established methods, across multiple natural l…
DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning
Department of Electrical and Computer Engineering, National University of Singapore, Singapore（电子与计算机工程系，新加坡国立大学）；Department of Computer Science, Birla Institute of Technology and Science, Pilani, India（计算机科学系，比拉理工学院与科学学院，印度）
Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning…
University of Electronic Science and Technology of China（电子科技大学）；The Chinese University of Hong Kong（香港中文大学）；Peng Cheng Lab（鹏城实验室）
Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically effective approach is to reduce the overall storage and computation costs of RNNs by network pruning techniques. Despite their successful applications, those pruning methods based on Lasso either produce irregular sparse patterns in weight matrices, which is not helpful in practical speedup. To address these issues, we propose structured pruning method thro…
The over-parametrized nature of Deep Neural Networks leads to considerable hindrances during deployment on low-end devices with time and space constraints. Network pruning strategies that sparsify DNNs using iterative prune-train schemes are often computationally expensive. As a result, techniques that prune at initialization, prior to training, have become increasingly popular. In this work, we propose neuron-to-neuron skip connections, which act as sparse weighted skip connections, to enhance the overall connectivity of pruned DNNs. Following a preliminary pruning step, N2NSkip connections a…
Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
Zhejiang University（浙江大学）；Shanghai Innovation Institute（上海创新研究院）；Southeast University（东南大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Suzhou Institute for Advanced Research, University of Science and Technology of China（中国科学技术大学苏州高等研究院）
Multi-Granular Node Pruning for Causal Circuit Discovery
Department of Computer Science, University of Kentucky, USA（美国肯塔基大学计算机科学系）；Department of Computer Science, Dalhousie University, Canada（加拿大达尔豪斯大学计算机科学系）
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Huazhong University of Science and Technology（华中科技大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Nanyang Technological University（南洋理工大学）
On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning
Department of Computer Science, TU Dortmund University（图恩-多特蒙德大学计算机科学系）；Bonn-Aachen International Center for Information Technology, University of Bonn（波恩-亚琛国际信息科技中心，波恩大学）；Computer Science School, University of Sheffield（谢菲尔德大学计算机科学学院）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能与机器学习研究所）
With the rapid development of deep learning, the sizes of neural networks become larger and larger so that the training and inference often overwhelm the hardware resources. Given the fact that neural networks are often over-parameterized, one effective way to reduce such computational overhead is neural network pruning, by removing redundant parameters from trained neural networks. It has been recently observed that pruning can not only reduce computational overhead but also can improve empirical robustness of deep neural networks (NNs), potentially owing to removing spurious correlations whi…
Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This paper offers the first survey concentrated on this emerging pruning fashion. We first introduce a generic formulation of neural network pruning, followed by the major classic pruning topics. Then, as the main body of this paper, a thorough and structured literature review of PaI methods is presented, consisting of two major tracks (sparse training and sparse selection). Finally, w…
Duke University（杜克大学）；Black Sesame Technologies（黑芝麻科技）
With the rapid scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for improving deployment efficiency. This work aims to advance the compression beyond the weights to neuron activations. We propose the joint regularization technique which simultaneously regulates the distribution of weights and activations. By distinguishing and leveraging the significance difference among neuron responses and connections during learning, the jointly pruned network, namely \textit{JPnet}, optimizes the sparsity of activa…
Transformer-based pre-trained language models have demonstrated superior performance on various natural language processing tasks. However, it remains unclear how the skills required to handle these tasks distribute among model parameters. In this paper, we find that after prompt tuning for specific tasks, the activations of some neurons within pre-trained Transformers are highly predictive of the task labels. We dub these neurons skill neurons and confirm they encode task-specific skills by finding that: (1) Skill neurons are crucial for handling tasks. Performances of pre-trained Transformer…
As one of the successful Transformer-based models in computer vision tasks, SegFormer demonstrates superior performance in semantic segmentation. Nevertheless, the high computational cost greatly challenges the deployment of SegFormer on edge devices. In this paper, we seek to design a lightweight SegFormer for efficient semantic segmentation. Based on the observation that neurons in SegFormer layers exhibit large variances across different images, we propose a dynamic gated linear layer, which prunes the most uninformative set of neurons based on the input instance. To improve the dynamically…
How much can pruning algorithms teach us about the fundamentals of learning representations in neural networks? And how much can these fundamentals help while devising new pruning techniques? A lot, it turns out. Neural network pruning has become a topic of great interest in recent years, and many different techniques have been proposed to address this problem. The decision of what to prune and when to prune necessarily forces us to confront our assumptions about how neural networks actually learn to represent patterns in data. In this work, we set out to test several long-held hypotheses abou…
University of Electronic Science and Technology of China（电子科技大学）；Clinical Hospital of Chengdu Brain Science Institute（成都脑科学医院）；MOE-K Lab for NeuroInformation（神经信息MOE-K实验室）；Int Institute of Brain-Apparatus Communication（脑机通讯国际研究所）；School of Life Science and Technology（生命科学与技术学院）
Unstructured neural network pruning algorithms have achieved impressive compression rates. However, the resulting - typically irregular - sparse matrices hamper efficient hardware implementations, leading to additional memory usage and complex control logic that diminishes the benefits of unstructured pruning. This has spurred structured coarse-grained pruning solutions that prune entire filters or even layers, enabling efficient implementation at the expense of reduced flexibility. Here we propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, k…
Lahore University of Management Sciences（拉合尔管理科学大学）
One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements. Deep CNNs can either be pruned width-wise by removing filters based on their importance or depth-wise by removing layers and blocks. Width wise pruning (filter pruning) is commonly performed via learnable gates or switches and sparsity regularizers whereas pruning of layers has so far been performed arbitrarily by manually designing a smaller network usually referred to as a student network. We propose a comprehensive pruning stra…
To prune or not to prune : A chaos-causality approach to principled pruning of dense neural networks
Birla Institute of Technology and Sciences Pilani（皮拉尼伯拉理工学院）；BITS Pilani, Goa Campus（皮拉尼伯拉理工学院果阿校区）；National Institute of Advanced Studies（国家高等研究院）；Nitte Meenakshi Institute of Technology（尼特·米纳克希理工学院）；HappyMonk AI（HappyMonk人工智能公司）
Modern-day neural networks are famously large, yet also highly redundant and compressible; there exist numerous pruning strategies in the deep learning literature that yield over 90% sparser sub-networks of fully-trained, dense architectures while still maintaining their original accuracies. Amongst these many methods though -- thanks to its conceptual simplicity, ease of implementation, and efficacy -- Iterative Magnitude Pruning (IMP) dominates in practice and is the de facto baseline to beat in the pruning community. However, theoretical explanations as to why a simplistic method such as IM…
University of Maryland（马里兰大学）；Shandong University（山东大学）
Network compression is crucial to making the deep networks to be more efficient, faster, and generalizable to low-end hardware. Current network compression methods have two open problems: first, there lacks a theoretical framework to estimate the maximum compression rate; second, some layers may get over-prunned, resulting in significant network performance drop. To solve these two problems, this study propose a gradient-matrix singularity analysis-based method to estimate the maximum network redundancy. Guided by that maximum rate, a novel and efficient hierarchical network pruning algorithm …
Pruning enables appealing reductions in network memory footprint and time complexity. Conventional post-training pruning techniques lean towards efficient inference while overlooking the heavy computation for training. Recent exploration of pre-training pruning at initialization hints on training cost reduction via pruning, but suffers noticeable performance degradation. We attempt to combine the benefits of both directions and propose a policy that prunes as early as possible during training without hurting performance. Instead of pruning at initialization, our method exploits initial dense t…
Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
Institute of Computing Technology, Chinese Academy of Science（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Laboratory（中关村实验室）；Sensetime Research（商汤科技研究院）
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Recent advances in the sparse neural network literature have made it possible to prune many large feed forward and convolutional networks with only a small quantity of data. Yet, these same techniques often falter when applied to the problem of recovering sparse recurrent networks. These failures are quantitative: when pruned with recent techniques, RNNs typically obtain worse performance than they do under a simple random pruning scheme. The failures are also qualitative: the distribution of active weights in a pruned LSTM or GRU network tend to be concentrated in specific neurons and gates, …
Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the first and second-order Taylor expansions to approximate a filter's contribution. Both methods scale consistently across any network layer without requiring per-layer sensitivity analysis and can be applied to any kind of layer, including skip connections. For modern networks trai…
