Related papers: Productive Development of Scalable Network Functio…
Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…
An effective packet processing abstraction that leverages software or hardware acceleration techniques can simplify the implementation of high-performance virtual network functions. In this paper, we explore the suitability of SDN switches'…
Spiking Neural Networks (SNNs) have sparse, event driven processing that can leverage neuromorphic applications. In this work, we introduce a multi-threading kernel that enables neuromorphic applications running at the edge, meaning they…
Service Function Chaining (SFC) allows the forwarding of a traffic flow along a chain of Virtual Network Functions (VNFs, e.g., IDS, firewall, and NAT). Software Defined Networking (SDN) solutions can be used to support SFC reducing the…
In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be…
Neural Module Network (NMN) exhibits strong interpretability and compositionality thanks to its handcrafted neural modules with explicit multi-hop reasoning capability. However, most NMNs suffer from two critical drawbacks: 1) scalability:…
Fully-strict fork-join parallelism is a powerful model for shared-memory programming due to its optimal time scaling and strong bounds on memory scaling. The latter is rarely achieved due to the difficulty of implementing continuation…
Applications are sets of interacting components that can be executed in sequence, in parallel, or by using more complex constructs such as selections and loops. They can, therefore, be modeled as structured graphs with sub-structures…
Network Function Virtualization (NFV) provides higher flexibility for network operators and reduces the complexity in network service deployment. Using NFV, Virtual Network Functions (VNF) can be located in various network nodes and chained…
In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of "constructive neural networks" in approximation theory, we focus on "constructing" rather than "training" feed-forward neural…
Spiking Neural Networks (SNNs) are brain-inspired, event-driven machine learning algorithms that have been widely recognized in producing ultra-high-energy-efficient hardware. Among existing SNNs, unsupervised SNNs based on synaptic…
The Apache Spark stack has enabled fast large-scale data processing. Despite a rich library of statistical models and inference algorithms, it does not give domain users the ability to develop their own models. The emergence of…
Graph processing systems are essential for analyzing large-scale data with complex relationships, yet most existing frameworks rely on statically provisioned clusters, resulting in poor elasticity and inefficient resource utilization under…
Recent research has shown that graph neural networks (GNNs) can learn policies for locomotion control that are as effective as a typical multi-layer perceptron (MLP), with superior transfer and multi-task performance (Wang et al., 2018;…
Inspired by biological processes, neuromorphic computing leverages spiking neural networks (SNNs) to perform inference tasks, offering significant efficiency gains for workloads involving sequential data. Recent advances in hardware and…
Network Function Virtualization (NFV) enables the "softwarization" of network functions, which are implemented on virtual machines hosted on Commercial off-the-shelf (COTS) servers. Both the composition of the virtual network functions…
As mobile network users look forward to the connectivity speeds of 5G networks, service providers are facing challenges in complying with connectivity demands without substantial financial investments. Network Function Virtualization (NFV)…
We propose an efficient distributed out-of-memory implementation of the Non-negative Matrix Factorization (NMF) algorithm for heterogeneous high-performance-computing (HPC) systems. The proposed implementation is based on prior work on…
Graph Neural Networks (GNNs) are powerful deep learning models to generate node embeddings on graphs. When applying deep GNNs on large graphs, it is still challenging to perform training in an efficient and scalable way. We propose a novel…
Nonnegative Matrix Factorization (NMF) aims to factorize a matrix into two optimized nonnegative matrices and has been widely used for unsupervised learning tasks such as product recommendation based on a rating matrix. However, although…