Related papers: Growing Efficient Accurate and Robust Neural Netwo…

Recently developed deep neural models like NetGAN, CELL, and Variational Graph Autoencoders have made progress but face limitations in replicating key graph statistics on generating large graphs. Diffusion-based methods have emerged as…

Energy harvesting (EH) IoT devices that operate intermittently without batteries, coupled with advances in deep neural networks (DNNs), have opened up new opportunities for enabling sustainable smart applications. Nevertheless, implementing…

Intelligent Internet of Things (IoT) systems based on deep neural networks (DNNs) have been widely deployed in the real world. However, DNNs are found to be vulnerable to adversarial examples, which raises people's concerns about…

When trained as generative models, Deep Learning algorithms have shown exceptional performance on tasks involving high dimensional data such as image denoising and super-resolution. In an increasingly connected world dominated by mobile and…

In safety-critical but computationally resource-constrained applications, deep learning faces two key challenges: lack of robustness against adversarial attacks and large neural network size (often millions of parameters). While the…

Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets. However, recent deep learning models have moved forward from…

Graph Neural Networks (GNNs) are vital for learning from graph-structured data, enabling applications in network analysis, recommendation systems, and speech analytics. Deploying them on edge devices like client PCs and laptops enhances…

The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial examples and have unstable gradients which hinders interpretability. However, existing methods to solve these issues, such as adversarial…

With the edge computing becoming an increasingly adopted concept in system architectures, it is expected its utilization will be additionally heightened when combined with deep learning (DL) techniques. The idea behind integrating demanding…

Machine learning models based on Deep Neural Networks (DNNs) are increasingly deployed in a wide range of applications ranging from self-driving cars to COVID-19 treatment discovery. To support the computational power necessary to learn a…

This paper introduces FlexNN, a Flexible Neural Network accelerator, which adopts agile design principles to enable versatile dataflows, enhancing energy efficiency. Unlike conventional convolutional neural network accelerator architectures…

The increasing scale and complexity of integrated circuit design have led to increased challenges in Electronic Design Automation (EDA). Graph Neural Networks (GNNs) have emerged as a promising approach to assist EDA design as circuits can…

Conventionally, DNN models are trained once in the cloud and deployed in edge devices such as cars, robots, or unmanned aerial vehicles (UAVs) for real-time inference. However, there are many cases that require the models to adapt to new…

Deep learning has been successfully adopted in mobile edge computing (MEC) to optimize task offloading and resource allocation. However, the dynamics of edge networks raise two challenges in neural network (NN)-based optimization methods:…

Modern deep learning workloads increasingly exhibit dynamic, metadata-driven execution, where runtime-generated information determines memory provisioning and kernel launch decisions. In sampling-based graph neural network (GNN) training,…

The field of computer vision has grown very rapidly in the past few years due to networks like convolution neural networks and their variants. The memory required to store the model and computational expense are very high for such a network…

We address the efficiency issue for the construction of a deep graph neural network (GNN). The approach exploits the idea of representing each input graph as a fixed point of a dynamical system (implemented through a recurrent neural…

In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models. We demonstrate that we can jointly optimize for accuracy, inference time, and the number of parameters by…

Machine learning (ML), especially deep learning is made possible by the availability of big data, enormous compute power and, often overlooked, development tools or frameworks. As the algorithms become mature and efficient, more and more ML…

Graph convolutional networks (GCNs) have been employed as a kind of significant tool on many graph-based applications recently. Inspired by convolutional neural networks (CNNs), GCNs generate the embeddings of nodes by aggregating the…