arXiv research

This paper optimizes AI inference on edge devices with reduced communication and computation costs.

Edge computing tackles dynamic data in IIoT with incremental learning.

Optimized neural networks for Edge TPU achieve high accuracy in real-time image classification.

A hybrid neural network optimizes AI deployment on edge and cloud for energy efficiency.

A simpler edge-based discretization method without dual volumes.

Coded Federated Learning speeds up training in edge computing networks.

In matrix factorization, available graph side-information may not be well suited for the matrix completion problem, having edges that disagree with the latent-feature relations learnt from the incomplete data matrix. We show that removing these $\textit{contested}$ edges improves prediction accuracy and scalability. We…

Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical so…

A new framework reduces data upload for image classification while protecting user privacy.

Paper presents a lightweight, unobtrusive method to protect edge device data privacy.

This work surveys attacks and defenses on edge neural networks.

Edge devices learn directly from personal data using spiking networks.

This paper proposes a new D2D data sharing approach to improve distributed machine learning training speed.

We propose an approach for approximating the partition function which is based on two steps: (1) computing the partition function of a simplified model which is obtained by deleting model edges, and (2) rectifying the result by applying an edge-by-edge correction. The approach leads to an intuitive framework in which o…

STORM enables edge computing for empirical risk minimization.

New method calibrates probabilistic linear solver for online coverage guarantees.

Researchers found the Wigner derivative and its inverse are equal for spherical tetrahedra.

We address the problem of computing a single linkage dendrogram. A possible approach is to: (i) Form an edge weighted graph $G$ over the data, with edge weights reflecting dissimilarities. (ii) Calculate the MST $T$ of $G$. (iii) Break the longest edge of $T$ thereby splitting it into subtrees $T_L$, $T_R$. (iv) Apply …

To accommodate heterogeneous tasks in Internet of Things (IoT), a new communication and computing paradigm termed mobile edge computing emerges that extends computing services from the cloud to edge, but at the same time exposes new challenges on security. The present paper studies online security-aware edge computing …

Intelligent transportation systems (ITSs) will be a major component of tomorrow's smart cities. However, realizing the true potential of ITSs requires ultra-low latency and reliable data analytics solutions that can combine, in real-time, a heterogeneous mix of data stemming from the ITS network and its environment. Su…

The PC algorithm allows investigators to estimate a complete partially directed acyclic graph (CPDAG) from a finite dataset, but few groups have investigated strategies for estimating and controlling the false discovery rate (FDR) of the edges in the CPDAG. In this paper, we introduce PC with p-values (PC-p), a fast al…

Survey examines data quality challenges in edge ML.

Local SGD outperforms conventional methods in LLM training.

Low-rank training improves neural network training on edge devices with non-volatile memory.

Developing active inference agents for edge devices with limited resources.

The paper provides conditions for realizing graphs and polytopes with specified edge lengths.

This paper quantizes CapsNets for efficient edge deployment.

SLIP secures LLMs on edge devices by splitting computation and protecting sensitive parts.

We describe the configuration space $\mathbf{S}$ of polygons with prescribed edge slopes, and study the perimeter $\mathcal{P}$ as a Morse function on $\mathbf{S}$. We characterize critical points of $\mathcal{P}$ (these are \textit{tangential} polygons) and compute their Morse indices. This setup is motivated by a num…

In the emerging advancement in the branch of autonomous robotics, the ability of a robot to efficiently localize and construct maps of its surrounding is crucial. This paper deals with utilizing thermal-infrared cameras, as opposed to conventional cameras as the primary sensor to capture images of the robot's surroundi…

We compute the differential geometric invariants of cuspidal edges on flat surfaces in hyperbolic $3$-space and in de Sitter space. Several dualities of invariants are pointed out.

Paper presents privacy-preserving techniques for HD computing.

As video camera deployments continue to grow, the need to process large volumes of real-time data strains wide area network infrastructure. When per-camera bandwidth is limited, it is infeasible for applications such as traffic monitoring and pedestrian tracking to offload high-quality video streams to a datacenter. Th…

The paper proposes a novel Kernelized image segmentation scheme for noisy images that utilizes the concept of Smallest Univalue Segment Assimilating Nucleus (SUSAN) and incorporates spatial constraints by computing circular colour map induced weights. Fuzzy damping coefficients are obtained for each nucleus or center p…

Secure asynchronous federated learning with differential privacy for edge intelligence.

Paper proposes an AutoML framework for efficient device-edge co-inference.

Suppose $C$ is a compact, $n$-edged two-cell of the centered dual decomposition of a locally finite set in the hyperbolic plane, a coarsening of the Delaunay tessellation which was introduced in the author's prior work. We describe an effectively computable lower bound on the area of $C$, given an $n$-tuple of positive…

Enhances neural network dynamics to boost computational capacity.

In the edge computing paradigm, mobile devices offload the computational tasks to an edge server by routing the required data over the wireless network. The full potential of edge computing becomes realized only if a smart device selects the most appropriate server in terms of the latency and energy consumption, among …

OL4EL optimizes edge learning on resource-constrained servers.

pAElla detects malware in DCs/SCs with high accuracy.

Study reveals limits of detecting local geometry in random graphs.

This paper tackles task offloading in edge computing systems with dynamic interactions.

Hyperideal tetrahedra are the fundamental building blocks of hyperbolic 3-manifolds with geodesic boundary. The study of their geometric properties (in particular, of their volume) has applications also in other areas of low-dimensional topology, like the computation of quantum invariants of 3-manifolds and the use of …

A framework for real-time edge intelligence using federated meta-learning.

By leveraging the concept of mobile edge computing (MEC), massive amount of data generated by a large number of Internet of Things (IoT) devices could be offloaded to MEC server at the edge of wireless network for further computational intensive processing. However, due to the resource constraint of IoT devices and wir…

Incremental methods for structure learning of pairwise Markov random fields (MRFs), such as grafting, improve scalability by avoiding inference over the entire feature space in each optimization step. Instead, inference is performed over an incrementally grown active set of features. In this paper, we address key compu…

Paper proposes MAMRL for efficient energy dispatch in self-powered edge computing systems.