Related papers: Automatic Sparse Connectivity Learning for Neural …
Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accuracy drop incurred by SNNs, especially at high pruning…
Spiking Neural Networks (SNNs) have gained significant attention due to the energy-efficient and multiplication-free characteristics. Despite these advantages, deploying large-scale SNNs on edge hardware is challenging due to limited…
Pre-trained large models attract widespread attention in recent years, but they face challenges in applications that require high interpretability or have limited resources, such as physical sensing, medical imaging, and bioinformatics.…
We explore a new perspective on adapting the learning rate (LR) schedule to improve the performance of the ReLU-based network as it is iteratively pruned. Our work and contribution consist of four parts: (i) We find that, as the ReLU-based…
Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of…
Federated Learning (FL) is a privacy-preserving distributed deep learning paradigm that involves substantial communication and computation effort, which is a problem for resource-constrained mobile and IoT devices. Model…
Fine-tuning is an important step in adapting foundation models such as large language models to downstream tasks. To make this step more accessible to users with limited computational budgets, it is crucial to develop fine-tuning methods…
Deep neural networks achieve state-of-the-art performance in a variety of tasks by extracting a rich set of features from unstructured data, however this performance is closely tied to model size. Modern techniques for inducing sparsity and…
Introducing sparsity in a neural network has been an efficient way to reduce its complexity while keeping its performance almost intact. Most of the time, sparsity is introduced using a three-stage pipeline: 1) train the model to…
We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their…
Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse…
There exist endless examples of dynamical systems with vast available data and unsatisfying mathematical descriptions. Sparse regression applied to symbolic libraries has quickly emerged as a powerful tool for learning governing equations…
Spiking Neural Networks (SNNs) have been attached great importance due to their biological plausibility and high energy-efficiency on neuromorphic chips. As these chips are usually resource-constrained, the compression of SNNs is thus…
Sparseness is a useful regularizer for learning in a wide range of applications, in particular in neural networks. This paper proposes a model targeted at classification tasks, where sparse activity and sparse connectivity are used to…
The main goal of network pruning is imposing sparsity on the neural network by increasing the number of parameters with zero value in order to reduce the architecture size and the computational speedup. In most of the previous research…
Network embedding aims to learn low-dimensional representations of nodes in a network, while the network structure and inherent properties are preserved. It has attracted tremendous attention recently due to significant progress in…
Spiking Neural Networks (SNNs) provide a promising framework for energy-efficient and biologically grounded computation; however, scalable learning in deep recurrent architectures with sparse connectivity remains a major challenge. In this…
Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs…
Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity. It mainly involves three…
The Broad Learning System (BLS) has gained significant attention for its computational efficiency and less network parameters compared to deep learning structures. However, the standard BLS relies on the pseudoinverse solution, which…