Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

12253749 · Jun 202019922001200920182026
48 results for internet-connected devices

Automated system forecasts safety and security issues in internet-connected devices.

problem Challenges in real-time large-scale forecasting by human experts.
method Developed a scalable and versatile forecasting system using models and methods.
result Automated short and long-term forecasts detect safety and security issues in internet-connected devices.

TinyBayes detects crop diseases from images on edge devices with high accuracy and minimal resources.

problem Automated disease detection for cocoa crops in resource-constrained settings.
method Combines YOLOv8-Nano for lesion localisation, MobileNetV3-Small for feature extraction, and Jacobi prior for Bayesian classification.
result Achieves 78.7% accuracy on Amini Cocoa Contamination Challenge dataset with 9.5 MB model size and 150 ms inference time.

AppsPred predicts smartphone app usage based on context.

problem Predicting personalized usage behavior of smartphone apps based on contexts.
method Random Forest machine learning technique considering multi-dimensional contexts.
result AppsPred significantly outperforms other machine learning approaches in predicting smartphone apps.

Optimal model diagnoses funduscopic images for ocular diseases.

problem Binary classification of funduscopic images for ocular diseases.
method Transfer learning using Xception base architecture, Adam optimizer, mean squared error loss function, and custom heuristic equation.
result 90% accuracy, 94% sensitivity, and 86% specificity achieved.

FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.

problem Inequality in resource allocation hinders participation from resource-constrained devices in federated learning.
method Zero-shot knowledge transfer through a server-assigned distillation process.
result FedZKT effectively transfers knowledge across heterogeneous on-device models without requiring comparable local training efforts.

On-device federated learning updates edge models by exchanging trained results.

problem Limited training data at edge devices due to model drift.
method OS-ELM for sequential training and autoencoder for anomaly detection, combined with federated learning.
result The proposed approach produces a merged model as accurately as traditional methods with lower costs.

A method for trust evaluation of devices in human-device coexistence systems.

problem Efficient trust evaluation of devices in systems with diverse physical and social attributes.
method Canonical correlation analysis-enhanced hypergraph self-supervised learning (HSLCCA).
result The proposed HSLCCA method significantly outperforms baseline algorithms in identifying trusted devices.

This paper optimizes how deep learning models are distributed across different devices.

problem Optimizing how large, complex neural networks are split across multiple devices.
method Identified and solved an optimization problem for device placement of DNN operators.
result Automated algorithms that solve the device placement problem for modern pipelined settings.

Distributed learning adapts to diverse devices, improving performance.

problem Training neural networks on devices with varying capabilities and resources.
method Each device trains a customized neural network, sharing parameters with others.
result Achieves higher rewards on more powerful devices without sacrificing weaker ones.

Paper tackles efficient allocation of multiple devices to users for AutoML services.

problem Allocating multiple devices to multiple users for AutoML services efficiently.
method Develops a multi-device, multi-tenant algorithm for GP-EI, achieving near-linear speedup.
result Achieves near-linear speedup when users are many more than devices.

Semi-decentralized federated learning combines device-to-server and device-to-device communications for faster convergence.

problem Faster convergence in federated learning with decentralized model training.
method Two timescale hybrid federated learning (TT-HF) with cooperative D2D model aggregations.
result Achieves sublinear convergence rate of O(1/t) with adaptive control algorithm.

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

problem Efficiently performing AI inference on resource-constrained edge devices with reduced communication and computation costs.
method A three-step framework for effective inference: model split point selection, communication-aware model compression, and task-oriented encoding of intermediate features.
result Our proposed framework achieves a better trade-off and significantly reduces inference latency compared to baseline methods.

SplitEasy trains ML models on mobile devices without server data transfer.

problem Training complex DL models on resource-limited mobile devices.
method Split learning approach where sensitive layers are trained locally, computationally intensive layers on server.
result SplitEasy trains models on mobile devices with minimal data transfer, near-constant time per sample.

FD and FAug reduce communication in on-device ML with non-IID data.

problem Minimize communication overhead in on-device ML with non-IID data.
method Federated distillation (FD) and federated augmentation (FAug).
result FD with FAug reduces communication by 26x while maintaining high accuracy.

Fog learning distributes ML model training across heterogeneous devices and networks.

problem Challenges with conventional federated learning in heterogeneous networks.
method Intelligent distribution of ML model training across nodes from edge devices to cloud servers.
result Enhanced federated learning with multi-layer hybrid framework considering network, heterogeneity, and proximity.

FedCluster accelerates federated learning convergence by cycling device groups.

problem Federated learning convergence issues with device-level data heterogeneity.
method FedCluster groups devices into clusters that cycle through learning rounds, boosting convergence with meta-updates.
result FedCluster achieves faster convergence in nonconvex optimization compared to FedAvg.

First semi-device independent quantum money scheme introduced, proving unforgeability.

problem Creating secure quantum money without full device independence.
method Inspired by semi-device independent quantum key distribution, relaxes mint's cooperation assumption.
result First unforgeable quantum money scheme with partially relaxed device independence.

SEFR is a fast, energy-efficient classifier for ultra-low power devices.

problem Running machine learning on battery-powered devices is challenging due to time and energy constraints.
method SEFR is an ultra-low power classifier with linear time complexity for training and testing.
result SEFR is 63 times faster and 70 times more energy efficient than state-of-the-art classifiers.

Secure and efficient distributed learning on devices with limited communication.

problem Limited communication and security in distributed on-device learning.
method Proposes SLSGD, a robust distributed optimization algorithm with efficient communication and attack tolerance.
result Stabilizes convergence and tolerates data poisoning on a small number of workers.

AMS improves video inference on edge devices by adapting a small model with online knowledge distillation.

problem High computation cost of Deep Neural Networks for real-time video inference on edge devices.
method AMS uses a remote server to continually train and adapt a small model on edge devices, using online knowledge distillation from a large model.
result 0.4--17.8 percent mean Intersection-over-Union improvement in video semantic segmentation.

Flower framework simplifies federated learning experiments on edge devices.

problem Realistic implementation of Federated Learning on edge devices is challenging.
method Developed a comprehensive federated learning framework, Flower, supporting large-scale experiments on heterogeneous devices.
result Flower enables federated learning experiments with up to 15M client size using only two high-end GPUs.

POET enables large neural network training on tiny devices with reduced energy.

problem Training large neural networks on memory-limited edge devices.
method Jointly optimizes rematerialization and paging for memory reduction, formulating an MILP for energy-efficient training.
result POET trains ResNet-18 and BERT within Cortex-M memory constraints, outperforming current methods in energy efficiency.

EmBench evaluates DNN performance on various devices, identifying bottlenecks.

problem Understanding compatibility between DNN architectures and hardware.
method Systematic evaluation of state-of-the-art DNNs on commodity devices.
result Identifies bottlenecks in DNN architectures for different hardware.

Defines devices and agents based on behavior, using computational theory.

problem Differentiating between systems described by mechanical and intentional stances.
method Formal definition of devices and agents, using Bayes' rule to calculate subjective probability based on behavior.
result Bayesian approach to distinguishing between mechanical and intentional systems.

Survey of knowledge distillation for resource-limited devices.

problem Deploying large deep learning models on resource-limited devices.
method Knowledge distillation using a smaller model trained with information from a larger model.
result A new metric (distillation metric) for comparing different knowledge distillation algorithms.

MetaDVFS uses device and application metadata to improve DVFS efficiency.

problem Improving energy efficiency in mobile platforms with diverse applications and hardware.
method Formulates DVFS as a multi-task reinforcement learning problem and introduces MetaDVFS, leveraging metadata for knowledge transfer.
result MetaDVFS achieves up to 26% improvement in Quality of Experience and up to 17% improvement in Performance-Power Ratio.

DarkneTZ protects edge devices from DNN model leaks using TEE and model partitioning.

problem Privacy risks of pre-trained DNNs on edge devices through membership inference attacks.
method Model partitioning into sensitive and untrusted parts, leveraging TEE.
result DarkneTZ provides reliable model privacy with minimal performance overhead.

TOCO framework compresses neural networks based on tolerance analysis.

problem Deploying large neural networks on edge devices with limited resources.
method TOCO uses tolerance analysis to perform fine-grained compression, allowing flexibility to hardware changes.
result Fine-grained compression of neural networks on edge devices.