Static sparse training is a promising route to efficient learning by committing to a fixed mask pattern, yet the constrained structure reduces robustness. Early pruning decisions can lock the network into a brittle structure that is difficult to escape, especially in deep reinforcement learning (RL) where the evolving policy continually shifts the training distribution. We propose Topology-Aware Revival (TAR), a lightweight one-shot post-pruning procedure that improves static sparsity without dynamic rewiring. After static pruning, TAR performs a single revival step by allocating a small reserve budget across layers according to topology needs, randomly uniformly reactivating a few previously pruned connections within each layer, and then keeping the resulting connectivity fixed for the remainder of training. Across multiple continuous-control tasks with SAC and TD3, TAR improves final return over static sparse baselines by up to +37.9% and also outperforms dynamic sparse training baselines with a median gain of +13.5%.
Training deep reinforcement learning (DRL) models usually requires high computation costs. Therefore, compressing DRL models possesses immense potential for training acceleration and model deployment. However, existing methods that generate small models mainly adopt the knowledge distillation-based approach by iteratively training a dense network. As a result, the training process still demands massive computing resources. Indeed, sparse training from scratch in DRL has not been well explored and is particularly challenging due to non-stationarity in bootstrap training. In this work, we propos…
Eindhoven University of Technology（埃因霍温理工大学）；University of Twente（特文特大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Sony AI（索尼人工智能研究院）
Deep reinforcement learning (DRL) agents are trained through trial-and-error interactions with the environment. This leads to a long training time for dense neural networks to achieve good performance. Hence, prohibitive computation and memory resources are consumed. Recently, learning efficient DRL agents has received increasing attention. Yet, current methods focus on accelerating inference time. In this paper, we introduce for the first time a dynamic sparse training approach for deep reinforcement learning to accelerate the training process. The proposed approach trains a sparse neural net…
Robustness in sparse artificial neural networks trained with adaptive topology
Dept. of Biological Physics, Eötvös Loránd University（生物物理学系，欧文·洛朗大学）；Semmelweis University, Faculty of Health and Public Administration, Health Services Management Training Centre（塞梅利维斯大学，公共健康与行政学院，卫生服务管理培训中心）；Center for Complex Networks and Systems Research（复杂网络与系统研究所以）；Luddy School of Informatics, Computing, and Engineering（信息学、计算与工程学院）；Indiana University Bloomington（印第安纳大学布卢明顿分校）
Rensselaer Polytechnic Institute（伦斯勒理工学院）；University of Massachusetts（马萨诸塞大学）
In established network architectures, shortcut connections are often used to take the outputs of earlier layers as additional inputs to later layers. Despite the extraordinary effectiveness of shortcuts, there remain open questions on the mechanism and characteristics. For example, why are shortcuts powerful? Why do shortcuts generalize well? In this paper, we investigate the expressivity and generalizability of a novel sparse shortcut topology. First, we demonstrate that this topology can empower a one-neuron-wide deep network to approximate any univariate continuous function. Then, we presen…
Long training times of deep neural networks are a bottleneck in machine learning research. The major impediment to fast training is the quadratic growth of both memory and compute requirements of dense and convolutional layers with respect to their information bandwidth. Recently, training `a priori' sparse networks has been proposed as a method for allowing layers to retain high information bandwidth, while keeping memory and compute low. However, the choice of which sparse topology should be used in these networks is unclear. In this work, we provide a theoretical foundation for the choice o…
Eindhoven University of Technology（埃因霍温理工大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；JD Explore Academy（京东探索研究院）；University of Twente（特文特大学）
Random pruning is arguably the most naive way to attain sparsity in neural networks, but has been deemed uncompetitive by either post-training pruning or sparse training. In this paper, we focus on sparse training and highlight a perhaps counter-intuitive finding, that random pruning at initialization can be quite powerful for the sparse training of modern neural networks. Without any delicate pruning criteria or carefully pursued sparsity structures, we empirically demonstrate that sparsely training a randomly pruned network from scratch can match the performance of its dense equivalent. Ther…
We present a method for inferring dense depth maps from images and sparse depth measurements by leveraging synthetic data to learn the association of sparse point clouds with dense natural shapes, and using the image as evidence to validate the predicted depth map. Our learned prior for natural shapes uses only sparse depth as input, not images, so the method is not affected by the covariate shift when attempting to transfer learned models from synthetic data to real ones. This allows us to use abundant synthetic data with ground truth to learn the most difficult component of the reconstructio…
University of Twente（特文特大学）；Eindhoven University of Technology（埃因霍温理工大学）；University of Jyväskylä（于韦斯屈莱大学）
Sparse neural networks attract increasing interest as they exhibit comparable performance to their dense counterparts while being computationally efficient. Pruning the dense neural networks is among the most widely used methods to obtain a sparse neural network. Driven by the high training cost of such methods that can be unaffordable for a low-resource device, training sparse neural networks sparsely from scratch has recently gained attention. However, existing sparse training algorithms suffer from various issues, including poor performance in high sparsity scenarios, computing dense gradie…
We address the issue of estimating the topology and dynamics of sparse linear dynamic networks in a hyperparameter-free setting. We propose a method to estimate the network dynamics in a computationally efficient and parameter tuning-free iterative framework known as SPICE (Sparse Iterative Covariance Estimation). The estimated dynamics directly reveal the underlying topology. Our approach does not assume that the network is undirected and is applicable even with varying noise levels across the modules of the network. We also do not assume any explicit prior knowledge on the network dynamics. …
Eindhoven University of Technology（埃因霍温理工大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Derby（德比大学）
Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general practice) artificial neural networks, too, should not have fully-connected layers. Here we propose sparse evolutionary training of artificial neural networks, an algorithm which evolves an initial sparse topology (Erdős-Rényi random graph) of two consecutive layers of neurons into a scale-free topology,…
MIT Department of Mathematics（麻省理工学院数学系）；MIT Lincoln Laboratory Supercomputing Center（麻省理工学院林肯实验室超级计算中心）
The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning edges from the underlying topology. The resulting neural network is known as a sparse neural network. More recent work has demonstrated the remarkable result that certain sparse DNNs can train to the same precision as dense DNNs at lower runtime and storage cost. An intriguing class of these sparse DNNs is the X-Nets, which are initialized and trained upon …
Delft University of Technology (TU Delft)（代尔夫特理工大学）；University of Michigan（密歇根大学）
In this paper, we are interested in learning the underlying graph structure behind training data. Solving this basic problem is essential to carry out any graph signal processing or machine learning task. To realize this, we assume that the data is smooth with respect to the graph topology, and we parameterize the graph topology using an edge sampling function. That is, the graph Laplacian is expressed in terms of a sparse edge selection vector, which provides an explicit handle to control the sparsity level of the graph. We solve the sparse graph learning problem given some training data in b…
A major goal in genomics is to properly capture the complex dynamical behaviors of gene regulatory networks (GRNs). This includes inferring the complex interactions between genes, which can be used for a wide range of genomics analyses, including diagnosis or prognosis of diseases and finding effective treatments for chronic diseases such as cancer. Boolean networks have emerged as a successful class of models for capturing the behavior of GRNs. In most practical settings, inference of GRNs should be achieved through limited and temporally sparse genomics data. A large number of genes in GRNs …
Sparse cubical complexes for efficient topology-preservation in image data
Weill Cornell Medicine（威尔康奈尔医学院）；Technical University of Munich（慕尼黑工业大学）；Imperial College London（伦敦帝国理工学院）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Cornell Tech（康奈尔科技校区）；Munich Data Science Institute（慕尼黑数据科学研究所）
Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable sparse model to that of the largest trainable dense model. In this paper we introduce a method to train sparse neural networks with a fixed parameter count and a fixed computational cost throughout training, without sacrificing accuracy relative to existing dense-to-sparse training methods. Our method updates the topology of the sparse network during traini…
Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns are still not able to fully exploit the underlying heterogeneous network environments. In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the ne…
Eindhoven University of Technology（埃因霍温理工大学）；University of Twente（特温特大学）
A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational time becomes prohibitively long for datasets with a large number of samples or a very high dimensional feature space. In this paper, we present a new efficient unsupervised method for feature selection based on sparse autoencoders. In particular, we propose a new sparse training algorithm that optimizes a model's sparse topology during training to pay attentio…
Eindhoven University of Technology（埃因霍温理工大学）；University of Twente（特温特大学）
Recent works on sparse neural network training (sparse training) have shown that a compelling trade-off between performance and efficiency can be achieved by training intrinsically sparse neural networks from scratch. Existing sparse training methods usually strive to find the best sparse subnetwork possible in one single run, without involving any expensive dense or pre-training steps. For instance, dynamic sparse training (DST), is capable of reaching a competitive performance of dense training by iteratively evolving the sparse topology during the course of training. In this paper, we argue…
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
Tongji Univerity（同济大学）；University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）；Hong Kong University of Science and Technology (Guangzhou Campus)（香港科技大学（广州校区））；Griffith University（格里菲斯大学）；Massachusetts Institute of Technology（麻省理工学院）
University of Pennsylvania（宾夕法尼亚大学）；Yale University（耶鲁大学）
In common real-world robotic operations, action and state spaces can be vast and sometimes unknown, and observations are often relatively sparse. How do we learn the full topology of action and state spaces when given only few and sparse observations? Inspired by the properties of grid cells in mammalian brains, we build a generative model that enforces a normalized pairwise distance constraint between the latent space and output space to achieve data-efficient discovery of output spaces. This method achieves substantially better results than prior generative models, such as Generative Adversa…
Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
Center for Complex Network Intelligence (CCNI)（复杂网络智能研究中心）；Dept. of Computer Science & Technology（计算机科学与技术系）；School of Biomedical Engineering（生物医学工程学院）；University of Padova（帕多瓦大学）；Canva Research（Canva研究）
Graph Neural Networks (GNNs) are versatile, powerful machine learning methods that enable graph structure and feature representation learning, and have applications across many domains. For applications critically requiring interpretation, attention-based GNNs have been leveraged. However, these approaches either rely on specific model architectures or lack a joint consideration of graph structure and node features in their interpretation. Here we present a model-agnostic framework for interpreting important graph structure and node features, Graph neural networks Including SparSe inTerpretabi…
Eindhoven University of Technology（埃因霍温理工大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；University of Twente（特文特大学）；Scuola Superiore Sant’Anna（圣安娜高等研究院）
Sparse neural networks are effective approaches to reduce the resource requirements for the deployment of deep neural networks. Recently, the concept of adaptive sparse connectivity, has emerged to allow training sparse neural networks from scratch by optimizing the sparse structure during training. However, comparing different sparse topologies and determining how sparse topologies evolve during training, especially for the situation in which the sparse structure optimization is involved, remain as challenging open questions. This comparison becomes increasingly complex as the number of possi…
Sparse deep neural networks have shown their advantages over dense models with fewer parameters and higher computational efficiency. Here we demonstrate constraining the synaptic weights on unit Lp-sphere enables the flexibly control of the sparsity with p and improves the generalization ability of neural networks. Firstly, to optimize the synaptic weights constrained on unit Lp-sphere, the parameter optimization algorithm, Lp-spherical gradient descent (LpSGD) is derived from the augmented Empirical Risk Minimization condition, which is theoretically proved to be convergent. To understand the…
