Dynamic Sparse Training (DST) periodically prunes and regrows connections, inducing a discrete dynamical mechanism over network topologies. At extreme sparsity ($\ge 99\%$), this dynamic tends to destroy input-output information pathways, and performance with standard magnitude/random updates degrades sharply. We formalize forward, backward, and functional reachability on layered sparse graphs, derive closed-form expectations for reachable neurons and edges, and show that Monte Carlo realizations match the theory. Guided by this reachability-based structure, we bias pruning toward non-functional edges and regrowth toward functionally consistent candidates. We introduce this reachability-driven modification of topology evolution as Reachability-guided in DST, referred to as guided DST. On CIFAR-10/100 and Tiny ImageNet, guided DST recovers large accuracy gaps versus unguided DST (up to $+14.4$ points at $99.9\%$ sparsity on CIFAR-100), and on MLP-Mixer guided DST remains trainable at $99.99\%$ sparsity while unguided random regrowth degrades sharply. These results cast extreme-sparse training as a connectivity-preserving dynamical process. Our implementation is publicly available at https://github.com/mzjaworski/ea_dst.
Network-oriented research has been increasingly popular in many scientific areas. In neuroscience research, imaging-based network connectivity measures have become the key for understanding brain organizations, potentially serving as individual neural fingerprints. There are major challenges in analyzing connectivity matrices including the high dimensionality of brain networks, unknown latent sources underlying the observed connectivity, and the large number of brain connections leading to spurious findings. In this paper, we propose a novel blind source separation method with low-rank structu…
On Balancing Sparsity with Reliable Connectivity in Distributed Network Design with Random K-out Graphs
Laboratory for Information & Decision Systems, Massachusetts Institute of Technology（麻省理工学院信息与决策系统实验室）；Intel Corporation（英特尔公司）；Department of Electrical & Computer Engineering and Cylab Security & Privacy Institute, Carnegie Mellon University（卡内基梅隆大学电气与计算机工程系和Cylab安全与隐私研究所）
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…
Academia Sinica（中央研究院）；KKBOX Inc.（KKBOX公司）；National Chengchi University（国立政治大学）
Cross-domain collaborative filtering (CF) aims to alleviate data sparsity in single-domain CF by leveraging knowledge transferred from related domains. Many traditional methods focus on enriching compared neighborhood relations in CF directly to address the sparsity problem. In this paper, we propose superhighway construction, an alternative explicit relation-enrichment procedure, to improve recommendations by enhancing cross-domain connectivity. Specifically, assuming partially overlapped items (users), superhighway bypasses multi-hop inter-domain paths between cross-domain users (items, resp…
We propose a novel way of reducing the number of parameters in the storage-hungry fully connected layers of a neural network by using pre-defined sparsity, where the majority of connections are absent prior to starting training. Our results indicate that convolutional neural networks can operate without any loss of accuracy at less than half percent classification layer connection density, or less than 5 percent overall network connection density. We also investigate the effects of pre-defining the sparsity of networks with only fully connected layers. Based on our sparsifying technique, we in…
Center for Security Theory and Algorithmic Research（安全理论与算法研究中心）；International Institute of Information Technology Hyderabad（海得拉巴国际信息技术学院）
Sparse neural networks are shown to give accurate predictions competitive to denser versions, while also minimizing the number of arithmetic operations performed. However current hardware like GPU's can only exploit structured sparsity patterns for better efficiency. Hence the run time of a sparse neural network may not correspond to the arithmetic operations required. In this work, we propose RBGP( Ramanujan Bipartite Graph Product) framework for generating structured multi level block sparse neural networks by using the theory of Graph products. We also propose to use products of Ramanujan g…
Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity
University of Alberta（阿尔伯塔大学）；Eindhoven University of Technology（埃因霍温理工大学）；University of Luxembourg（卢森堡大学）；Alberta Machine Intelligence Institute（阿尔伯塔人工智能研究所）
This paper considers joint learning of multiple sparse Granger graphical models to discover underlying common and differential Granger causality (GC) structures across multiple time series. This can be applied to drawing group-level brain connectivity inferences from a homogeneous group of subjects or discovering network differences among groups of signals collected under heterogeneous conditions. By recognizing that the GC of a single multivariate time series can be characterized by common zeros of vector autoregressive (VAR) lag coefficients, a group sparse prior is included in joint regular…
University of Toronto（多伦多大学）；Modiface, Inc.（Modiface公司）；University of Guelph（圭尔夫大学）；Vector Institute（向量研究所）
Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different attention patterns by limiting a fixed number of spatially nearby tokens to accelerate the ViT's multi-head self-attention (MHSA) operations. However, such structured attention patterns limit the token-to-token connections to their spatial relevance, which disregards learned semantic connections from a full attention mask. In this work, we propose a novel approach…
University of Science and Technology of China（中国科学技术大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of California, Irvine（加州大学欧文分校）
Recent studies demonstrate that deep networks, even robustified by the state-of-the-art adversarial training (AT), still suffer from large robust generalization gaps, in addition to the much more expensive training costs than standard training. In this paper, we investigate this intriguing problem from a new perspective, i.e., injecting appropriate forms of sparsity during adversarial training. We introduce two alternatives for sparse adversarial training: (i) static sparsity, by leveraging recent results from the lottery ticket hypothesis to identify critical sparse subnetworks arising from t…
Neuro-inspired Ensemble-to-Ensemble Communication Primitives for Sparse and Efficient ANNs
Archimedes, Athena Research Center（阿基米德研究中心）；Harvard Medical School（哈佛医学院）；University of Crete（希腊克里特大学）；Foundation for Research and Technology-Hellas（希腊研究与技术基金会）
EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning
Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳））；Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen, China（深圳湾实验室神经疾病研究院）
Duke University, Fuqua School of Business（杜克大学富卡商学院）；Institute for Data, Systems, and Society, MIT（麻省理工学院数据、系统与社会研究所）；Operations Research Center, MIT（麻省理工学院运筹学中心）
We consider a seller offering a large network of $N$ products over a time horizon of $T$ periods. The seller does not know the parameters of the products' linear demand model, and can dynamically adjust product prices to learn the demand model based on sales observations. The seller aims to minimize its pseudo-regret, i.e., the expected revenue loss relative to a clairvoyant who knows the underlying demand model. We consider a sparse set of demand relationships between products to characterize various connectivity properties of the product network. In particular, we study three different spars…
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,…
University of Sussex（萨塞克斯大学）；Moogsoft Ltd（穆格软件有限公司）；Moogsoft Inc（穆格软件股份有限公司）
We consider the problem of inferring the functional connectivity of a large-scale computer network from sparse time series of events emitted by its nodes. We do so under the following three domain-specific constraints: (a) non-stationarity of the functional connectivity due to unknown temporal changes in the network, (b) sparsity of the time-series of events that limits the effectiveness of classical correlation-based analysis, and (c) lack of an explicit model describing how events propagate through the network. Under the assumption that the probability of two nodes being functionally connect…
Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One approach to overcoming this limit is the design of sparse neural networks, which can be both very large and efficiently trained. In this paper we experiment training on sparse neural network topologies. We test pruning-based topologies, which are derived from an initially dense network whose connections are pruned, as well as RadiX-Nets, a class of network topo…
Sparse Network Inference under Imperfect Detection and its Application to Ecological Networks
Department of Electrical and Computer Engineering and the Ken Kennedy Institute（电气与计算机工程系和肯尼迪研究所）；Department of Computational and Applied Mathematics at Rice University（里士满大学计算与应用数学系）；SISTEMIC, Facultad de Ingeniería, Universidad de Antioquia（安提奥基亚大学工程学院SISTEMIC）
University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）；Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS)（三校神经影像与数据科学转化研究中心（TReNDS））；Georgia State University（佐治亚州立大学）；Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）
Independent component analysis (ICA) of multi-subject functional magnetic resonance imaging (fMRI) data has proven useful in providing a fully multivariate summary that can be used for multiple purposes. ICA can identify patterns that can discriminate between healthy controls (HC) and patients with various mental disorders such as schizophrenia (Sz). Temporal functional network connectivity (tFNC) obtained from ICA can effectively explain the interactions between brain networks. On the other hand, dictionary learning (DL) enables the discovery of hidden information in data using learnable basi…
Xiamen University（厦门大学）；Southern Illinois University Carbondale（南伊利诺伊大学卡本代尔分校）；Kneron Inc.（耐能智慧股份有限公司）；Yulin Normal University（玉林师范学院）
Since sparse neural networks usually contain many zero weights, these unnecessary network connections can potentially be eliminated without degrading network performance. Therefore, well-designed sparse neural networks have the potential to significantly reduce FLOPs and computational resources. In this work, we propose a new automatic pruning method - Sparse Connectivity Learning (SCL). Specifically, a weight is re-parameterized as an element-wise multiplication of a trainable weight variable and a binary mask. Thus, network connectivity is fully described by the binary mask, which is modulat…
