A novel method to identify salient computational paths within randomly wired neural networks before training is proposed. The computational graph is pruned based on a node mass probability function defined by local graph measures and weighted by hyperparameters produced by a reinforcement learning-based controller neural network. We use the definition of Ricci curvature to remove edges of low importance before mapping the computational graph to a neural network. We show a reduction of almost $35\%$ in the number of floating-point operations (FLOPs) per pass, with no degradation in performance. Further, our method can successfully regularize randomly wired neural networks based on purely structural properties, and also find that the favourable characteristics identified in one network generalise to other networks. The method produces networks with better performance under similar compression to those pruned by lowest-magnitude weights. To our best knowledge, this is the first work on pruning randomly wired neural networks, as well as the first to utilize the topological measure of Ricci curvature in the pruning mechanism.
Northeastern University（东北大学）；Syracuse University（雪城大学）；DiDi AI Labs（滴滴人工智能实验室）；University of Michigan（密歇根大学）
Structured weight pruning is a representative model compression technique of DNNs to reduce the storage and computation requirements and accelerate inference. An automatic hyperparameter determination process is necessary due to the large number of flexible hyperparameters. This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose a…
Existing high-performance deep learning models require very intensive computing. For this reason, it is difficult to embed a deep learning model into a system with limited resources. In this paper, we propose the novel idea of the network compression as a method to solve this limitation. The principle of this idea is to make iterative pruning more effective and sophisticated by simulating the reduced network. A simple experiment was conducted to evaluate the method; the results showed that the proposed method achieved higher performance than existing methods at the same pruning level.
Application of discrete Ricci curvature in pruning randomly wired neural networks: A case study with chest x-ray classification of COVID-19
The Institute of Mathematical Sciences (IMSc), Chennai 600113, India（数学科学研究所）；Institute of Computer Science（计算机科学研究所）；Homi Bhabha National Institute (HBNI), Mumbai 400094, India（霍米·巴哈瓦国家研究所）
Virginia Tech（弗吉尼亚理工学院）；Howard University（霍华德大学）；West Virginia University（西弗吉尼亚大学）
Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the conducted research efforts, the sparsity is enforced for network pruning without any attention to the internal network characteristics such as unbalanced outputs of the neurons or more specifically the distribution of the weights and outputs of the neurons. That may cause severe accuracy drop due to uncontrolled sparsity. In this work, we propose an attentio…
Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a common approach to reduce the size of CNNs, pruning methods delete part of the CNN filters according to some metrics such as $l1$-norm. However, previous methods hardly leverage the information variance in a single feature map and the similarity characteristics among feature maps. In this paper, we propose a novel filter pruning method, which incorporates two kinds of feature map selections: diversity-aware selection…
Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs
1 Brandenburg Technical University, Cottbus, Germany；2 University of Zanjan, Iran；3 Tallinn University of Technology, Estonia；4 Leibniz Institute for High Performance Microelectronics, Frankfurt Oder, Germany
Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach
Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Mathematics and Statistics, Shandong University（山东大学数学与统计学院）；School of Artificial Intelligence, Beihang University（北航人工智能学院）；School of Mathematics, Shandong University（山东大学数学学院）
Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
National Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
School of Electronics and Computer Science, University of Southampton, UK（索姆塞特大学电子与计算机科学学院）；Department of Computer Science, University of Liverpool, UK（利弗pool大学计算机科学系）
Lightweight Intrusion Detection in IoT via SHAP-Guided Feature Pruning and Knowledge-Distilled Kronecker Networks
LSIA Laboratory, Moroccan School of Engineering Sciences (EMSI)（摩洛哥工程科学学校LSIA实验室）；Laboratory of Research in Informatics (LaRI), Faculty of Sciences, Ibn Tofail University（伊本·泰菲勒大学信息研究实验室）；College of Computing, University Mohammed VI Polytechnic（穆莱·伊沙克六世理工学院计算机学院）
In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Exp…
SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Zhejiang University of Technology（浙江工业大学）；Nanyang Technological University（南洋理工大学）；Zhejiang University（浙江大学）；Southwest University（西南大学）；The City College of New York（纽约城市学院）；Shenzhen University of Advanced Technology（深圳大学）
Certificate-Guided Pruning for Stochastic Lipschitz Optimization
Department of Computer Science, Iowa State University, Ames, Iowa, USA；Department of Civil, Construction \& Environmental Engineering, Iowa State University, Ames, Iowa, USA
Université de Montréal（蒙特利尔大学）；MILA；IMT Atlantique（IMT大西洋高等矿业学院）；Lab-STICC（STICC实验室）；ISCAS 2019（ISCAS 2019（会议名称，不提取））
Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and strongly limits their usability in budget-constrained devices such as embedded devices. In this paper, we propose a combination of a new pruning technique and a quantization scheme that effectively reduce the complexity and memory usage of convolutional layers of CNNs, and replace the complex convolutional operation by a low-cost multiplexer. We perform experimen…
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；Nanyang Technological University（南洋理工大学）
Conventional NAS-based pruning algorithms aim to find the sub-network with the best validation performance. However, validation performance does not successfully represent test performance, i.e., potential performance. Also, although fine-tuning the pruned network to restore the performance drop is an inevitable process, few studies have handled this issue. This paper provides a novel Ensemble Knowledge Guidance (EKG) to solve both problems at once. First, we experimentally prove that the fluctuation of loss landscape can be an effective metric to evaluate the potential performance. In order t…
FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification
Media IC and System Lab, the Graduate Institute of Electronics Engineering and Department of Electrical Engineering, National Taiwan University（媒体IC与系统实验室，电子工程研究所及电气工程系，国立台湾大学）
Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
Data Science Center ScaDS.AI, Universität Leipzig（ScaDS.AI数据科学中心，莱比锡大学）；Department of Artificial Intelligence, Fraunhofer Heinrich-Hertz-Institute（人工智能系，弗劳恩霍夫 Heinrich-Hertz 研究所）；Department of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学系，柏林技术大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Centre of eXplainable Artificial Intelligence, Technological University Dublin（可解释人工智能中心，都柏林技术大学）
Harvard University（哈佛大学）；MIT（麻省理工学院）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）；IBM Research Europe（IBM欧洲研究院）
High-throughput virtual screening is an indispensable technique utilized in the discovery of small molecules. In cases where the library of molecules is exceedingly large, the cost of an exhaustive virtual screen may be prohibitive. Model-guided optimization has been employed to lower these costs through dramatic increases in sample efficiency compared to random selection. However, these techniques introduce new costs to the workflow through the surrogate model training and inference steps. In this study, we propose an extension to the framework of model-guided optimization that mitigates infe…
Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
University of Arizona（亚利桑那大学）；Bosch Center for AI（博世人工智能中心）；GE HealthCare（GE医疗）；College of William and Mary（威廉玛丽学院）；Purdue University（普渡大学）；University of Maryland（马里兰大学）；University of Pittsburgh（匹兹堡大学）
本文提出 Auto-Train-Once (ATO) 网络剪枝算法，通过引入控制器网络指导目标模型权重学习并采用新颖随机梯度算法增强训练协调，解决了现有 OTO 方法局部最优收敛问题，在多个标准数据集和模型架构上实现最先进性能。
Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning
The School of Computing and Information Systems, the University of Melbourne, Melbourne, Australia（墨尔本大学计算与信息系统学院）；Royal Melbourne Institute of Technology, Melbourne, Australia（皇家墨尔本理工学院）；Now at Google Australia（现就职于谷歌澳大利亚）
The computation and memory needed for Convolutional Neural Network (CNN) inference can be reduced by pruning weights from the trained network. Pruning is guided by a pruning saliency, which heuristically approximates the change in the loss function associated with the removal of specific weights. Many pruning signals have been proposed, but the performance of each heuristic depends on the particular trained network. This leaves the data scientist with a difficult choice. When using any one saliency metric for the entire pruning process, we run the risk of the metric assumptions being invalidat…
Singapore University of Technology and Design（新加坡科技设计大学）
Dependency trees convey rich structural information that is proven useful for extracting relations among entities in text. However, how to effectively make use of relevant information while ignoring irrelevant information from the dependency trees remains a challenging research question. Existing approaches employing rule based hard-pruning strategies for selecting relevant partial dependency structures may not always yield optimal results. In this work, we propose Attention Guided Graph Convolutional Networks (AGGCNs), a novel model which directly takes full dependency trees as inputs. Our mo…
UC Berkeley（加州大学伯克利分校）；Facebook AI Research（脸书人工智能研究院）；KAUST（阿卜杜拉国王科技大学）；Stanford University（斯坦福大学）
Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the parameters' \textit{importance}. In contrast, we propose Uncertainty-guided Continual Bayesian Neural Networks (UCB), where the learning rate adapts according to the uncertainty defined in the probability distribution of the weights in networks. Uncertainty is a na…
Recovering Manifold Structure Using Ollivier-Ricci Curvature
Department of Computer Science, Columbia University（哥伦比亚大学计算机科学系）；Department of Statistics & Data Science, Wu Tsai Institute, Yale University（耶鲁大学统计与数据科学系、吴氏研究所）；Department of Mathematics, Columbia University（哥伦比亚大学数学系）；Irving Institute for Cancer Dynamics, Columbia University（哥伦比亚大学伊文斯癌症动力学研究所）
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 …
PARIS: Pruning Algorithm via the Representer theorem for Imbalanced Scenarios
Department of Physics and Astronomy（物理与天文学系）；Queen Mary University of London（伦敦女王玛丽大学）；University of Colorado（科罗拉多大学）；SWx-TREC (Space Weather Technology Research and Education Center)（空间天气技术研究与教育中心）
