Awesome Edge AI Papers

A curated list of Edge AI papers. If you find some interesting work/projects, please contact me through issues or email withhaotian [at] gmail [dot] com.

The papers or projects for on-device LLMs/SLMs are transferred to awesome-on-device-LLM-papers

Contributing

🔥 This list will be keep maintaining.

Contributions are always welcome! Please refer to our contributing guidelines for more information and create a PR to add papers or projects.

License

This project is licensed under the GPL-3.0 license - see the LICENSE file for details.

Overview

• Awesome Edge AI Papers
• Contributing
• License
• Overview
  • Surveys
  • Edge Training
  • Edge Inference
  • Serverless Computing
  • Large Language Models (LLMs) / Small Language Models (SLMs)
  • Graph Processing/Scheduling
  • Optimization for Edge systems
  • Edge AI Systems
  • System-Level Analytics & Evaluation
  • Edge Security & Privacy
  • On-Device Intelligence
  • Video Analytics
  • Edge Cahcing
  • Edge Data Storage/Analytics
  • Cloud-Edge Systems
  • Services Provision
  • Sensing & Wireless Communications
  • Unmanned Aerial Vehicle (UAV)
  • Mobile Crowdsensing
  • Resource Allocation/Management
  • Over-the-air Computation
  • Coded Distributed Computing

Surveys

• [KDD'24] Inference Optimization of Foundation Models on AI Accelerators - [PDF]
• [TPAMI'24] Parallel and distributed graph neural networks: An in-depth concurrency analysis - [PDF]
• [COMST'24] Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services - [PDF]
• [ACM CSUR'24] Mobile Edge Computing and Machine Learning in the Internet of Unmanned Aerial Vehicles: A Survey - [PDF]
• [ACM CSUR'24] A Model and Survey of Distributed Data-Intensive Systems - [PDF]
• [arXiv'24] On-Device Language Models: A Comprehensive Review - [PDF] [Code]
• [arXiv'24] A Survey of Small Language Models - [PDF]
• [arXiv'24] Small Language Models: Survey, Measurements, and Insights - [PDF] [Code] [Demo]
• [arXiv'24] A Survey of Resource-efficient LLM and Multimodal Foundation Models - [PDF] [Code]
• [arXiv'24] Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security - [PDF] [Code]
• [arXiv'24] Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence - [PDF]
• [arXiv'24] A Survey on Effective Invocation Methods of Massive LLM Services - [PDF]
• [arXiv'24] On-Device Language Models: A Comprehensive Review - [PDF]
• [arXiv'24] A Survey on Model Compression for Large Language Models - [PDF]
• [ACM CSUR'23] The evolution of distributed systems for graph neural networks and their origin in graph processing and deep learning: A survey - [PDF]
• [COMST'23] Distributed artificial intelligence empowered by end-edge-cloud computing: A survey - [PDF]
• [COMST'23] Machine Learning for Large-Scale Optimization in 6G Wireless Networks - [PDF]
• [IEEE JPROC'23] Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review - [PDF]
• [IOTJ'23] The Security and Privacy of Mobile Edge Computing: An Artificial Intelligence Perspective - [PDF]
• [COMST'22] Pervasive AI for IoT applications: A survey on resource-efficient distributed artificial intelligence - [PDF]

Edge Training

• [INFOCOM'24] Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration - [PDF]
• [INFOCOM'24] Edge-MSL: Split Learning on the Mobile Edge via Multi-Armed Bandits - [PDF]
• [INFOCOM'24] Heroes: Lightweight Federated Learning with Neural Composition and Adaptive Local Update in Heterogeneous Edge Networks - [PDF]
• [INFOCOM'24] SpreadFGL: Edge-Client Collaborative Federated Graph Learning with Adaptive Neighbor Generation - [PDF]
• [INFOCOM'24] Towards Efficient Asynchronous Federated Learning in Heterogeneous Edge Environments - [PDF]
• [WWW'24] Accelerating the Decentralized Federated Learning via Manipulating Edges - [PDF]
• [WWW'24] FedDSE: Distribution-aware Sub-model Extraction for Federated Learning over Resource-constrained Devices - [PDF]
• [WWW'24] How Few Davids Improve One Goliath: Federated Learning in Resource-Skewed Edge Computing Environments - [PDF]
• [TMC'24] Federated Learning with Dynamic Epoch Adjustment and Collaborative Training in Mobile Edge Computing - [PDF]
• [arXiv'24] Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models - [PDF]
• [TMC'23] HierFedML: aggregator placement and UE assignment for hierarchical federated learning in mobile edge computing - [PDF]
• [WWW'23] PipeEdge: A Trusted Pipelining Collaborative Edge Training based on Blockchain - [PDF]
• [WWW'23] FlexiFed: Personalized Federated Learning for Edge Clients with Heterogeneous Model Architectures - [PDF]
• [WWW'23] FedEdge: Accelerating Edge-Assisted Federated Learning - [PDF]
• [WWW'23] EdgeMove: Pipelining Device-Edge Model Training for Mobile Intelligence - [PDF]
• [WWW'23] pFedPrompt: Learning Personalized Prompt for Vision-Language Models in Federated Learning - [PDF]
• [TWC'23] Ensemble Distillation Based Adaptive Quantization for Supporting Federated Learning in Wireless Networks - [PDF]
• [TWC'23] Hierarchical Federated Learning With Quantization: Convergence Analysis and System Design - [PDF]
• [TWC'23] Knowledge-Guided Learning for Transceiver Design in Over-the-Air Federated Learning - [PDF]
• [TWC'23] Online Client Selection for Asynchronous Federated Learning With Fairness Consideration - [PDF]
• [TWC'23] Olive Branch Learning: A Topology-Aware Federated Learning Framework for Space-Air-Ground Integrated Network - [PDF]
• [TPDS'23] From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization - [PDF]
• [TPDS'23] Energy-Aware, Device-to-Device Assisted Federated Learning in Edge Computing - [PDF]
• [TPDS'23] HiFlash: Communication-Efficient Hierarchical Federated Learning With Adaptive Staleness Control and Heterogeneity-Aware Client-Edge Association - [PDF]
• [TPDS'23] HierFedML: Aggregator Placement and UE Assignment for Hierarchical Federated Learning in Mobile Edge Computing - [PDF]
• [ToN'23] Scheduling In-Band Network Telemetry With Convergence-Preserving Federated Learning - [PDF]
• [ToN'23] Optimizing Parameter Mixing Under Constrained Communications in Parallel Federated Learning - [PDF]
• [TMC'23] Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach - [PDF]
• [TMC'23] A Personalized Privacy Preserving Mechanism for Crowdsourced Federated Learning - [PDF]
• [TMC'23] Mobile Collaborative Learning over Opportunistic Internet of Vehicles - [PDF]
• [TMC'23] Tree Learning: Towards Promoting Coordination in Scalable Multi-Client Training Acceleration - [PDF]
• [TMC'23] PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models - Federated Learning in Age of Foundation Model - [PDF]
• [TMC'23] Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspective - [PDF]
• [TMC'23] Energy or Accuracy? Near-Optimal User Selection and Aggregator Placement for Federated Learning in MEC - [PDF]
• [TKDE'23] Adaptive Clustering based Personalized Federated Learning Framework for Next POI Recommendation with Location Noise - [PDF]
• [TGCN'23] Exploiting UAV for Air–Ground Integrated Federated Learning: A Joint UAV Location and Resource Optimization Approach - [PDF]
• [TC'23] Towards Data-Independent Knowledge Transfer in Model-Heterogeneous Federated Learning - [PDF]
• [JSTSP'23] Knowledge Selection and Local Updating Optimization for Federated Knowledge Distillation With Heterogeneous Models - [PDF]
• [JSAC'23] nFEDge: A Blockchain-Based Incentive Mechanism in Hierarchical Federated Learning for End-Edge-Cloud Communications - [PDF]
• [IOTJ'23] Multicore Federated Learning for Mobile-Edge Computing Platforms - [PDF]
• [INFOCOM'23] Joint Edge Aggregation and Association for Cost-Efficient Multi-Cell Federated Learning - [PDF]
• [INFOCOM'23] Communication-Efficient Federated Learning for Heterogeneous Edge Devices Based on Adaptive Gradient Quantization - [PDF]
• [INFOCOM'23] AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devices - [PDF]
• [INFOCOM WKSHPS'23] Federated Learning at the Edge: An Interplay of Mini-batch Size and Aggregation Frequency - [PDF]
• [ICC WKSHPS'23] Decentralized Federated Learning With Asynchronous Parameter Sharing - [PDF]
• [ICASSP'23] Semi-Federated Learning for Edge Intelligence with Imperfect SIC - [PDF]
• [arXiv'23] FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data - [PDF]
• [arXiv'23] Understanding Model Averaging in Federated Learning on Heterogeneous Data - [PDF]
• [arXiv'23] MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates - [PDF]
• [arXiv'23] Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning - [PDF]
• [arXiv'23] Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher - [PDF]
• [arXiv'23] Binary Federated Learning with Client-Level Differential Privacy - [PDF]
• [arXiv'23] Feature Matching Data Synthesis for Non-IID Federated Learning - [PDF]
• [arXiv'23] FedCiR: Client-Invariant Representation Learning for Federated Non-IID Features - [PDF]
• [arXiv'23] Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices - [PDF]
• [arXiv'23] FedAdapter: Efficient Federated Learning for Modern NLP - [PDF]
• [arXiv'23] Device-centric Federated Analytics At Ease - [PDF]
• [arXiv'23] Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing - [PDF]
• [arXiv'23] When Computing Power Network Meets Distributed Machine Learning: An Efficient Federated Split Learning Framework - [PDF]
• [WCNC'22] Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Data - [PDF]
• [TPDS'22] Reputation-Aware Hedonic Coalition Formation for Efficient Serverless Hierarchical Federated Learning - [PDF]
• [TPDS'22] PS+: A Simple yet Effective Framework for Fast Training on Parameter Server - [PDF]
• [TPDS'22] Incentive-Aware Autonomous Client Participation in Federated Learning - [PDF]
• [TON'22] Accelerating Federated Learning via Parallel Servers: A Theoretically Guaranteed Approach - [PDF]
• [TMC'22] FLASH: Heterogeneity-Aware Federated Learning at Scale - [PDF]
• [TMC'22] Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective - [PDF]
• [TITS'22] Federated Learning Enabled Credit Priority Task Processing for Transportation Big Data - [PDF]
• [TBD'22] Resource-Aware Federated Neural Architecture Search over Heterogeneous Mobile Devices - [PDF]
• [SenSys'22] TailorFL: Dual-Personalized Federated Learning under System and Data Heterogeneity - [PDF]
• [SECON'22] Energy-efficient Federated Learning via Stabilization-aware On-device Update Scaling - [PDF]
• [MobiSys'22] Melon: breaking the memory wall for resource-efficient on-device machine learning - [PDF]
• [MobiSys'22] FedBalancer: data and pace control for efficient federated learning on heterogeneous clients - [PDF]
• [INFOCOM'22] A Profit-Maximizing Model Marketplace with Differentially Private Federated Learning - [PDF]
• [arXiv'22] Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning - [PDF]
• [arXiv'22] FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers - [PDF]

Edge Inference

• [TMC'24] DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference - [PDF]
• [TMC'24] Distributed DNN Inference with Fine-grained Model Partitioning in Mobile Edge Computing Networks - [PDF]
• [WWW'24] Unlocking the Non-deterministic Computing Power with Memory-Elastic Multi-Exit Neural Networks - [PDF]
• [TMC'24] MoEI: Mobility-Aware Edge Inference Based on Model Partition and Service Migration - [PDF]
• [TSC'24] Incentive-Aware Partitioning and Offloading Scheme for Inference Services in Edge Computing - [PDF]
• [TMC'23] EdgeAdaptor: Online configuration adaption, model selection and resource provisioning for edge DNN inference serving at scale - [PDF]
• [TMC'23] PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices - [PDF]
• [INFOCOM'23] Cross-Camera Inference on the Constrained Edge - [PDF]
• [INFOCOM'23] Adversarial Group Linear Bandits and Its Application to Collaborative Edge Inference - [PDF]
• [ToN'23] Accelerating DNN Inference With Reliability Guarantee in Vehicular Edge Computing - [PDF]
• [TWC'23] Task-Oriented Communication for Edge Video Analytics - [PDF]
• [TWC'23] Progressive Feature Transmission for Split Classification at the Wireless Edge - [PDF]
• [OSDI'23] Optimizing Dynamic Neural Networks with Brainstorm - [PDF]
• [TMC'23] AdaEvo: Edge-Assisted Continuous and Timely DNN Model Evolution for Mobile Devices - [PDF]
• [JSAC'23] Resource Allocation for Multiuser Edge Inference With Batching and Early Exiting - [PDF]
• [JSAC'23] GNN at the Edge: Cost-Efficient Graph Neural Network Processing Over Distributed Edge Servers - [PDF]
• [ICSOC'23] Niagara: Scheduling DNN Inference Services on Heterogeneous Edge Processors - [PDF]
• [arXiv'23] Task-Oriented Communication with Out-of-Distribution Detection: An Information Bottleneck Framework - [PDF]
• [arXiv'23] Joint Batching and Scheduling for High-Throughput Multiuser Edge AI with Asynchronous Task Arrivals - [PDF]
• [arXiv'23] Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource - [PDF]
• [arXiv'23] Serving MoE Models on Resource-constrained Edge Devices via Dynamic Expert Swapping - [PDF]
• [arXiv'23] Accelerating In-Browser Deep Learning Inference on Diverse Edge Clients through Just-in-Time Kernel Optimizations - [PDF]
• [TWC'22] Task-Oriented Communication for Multi-Device Cooperative Edge Inference - [PDF]
• [TWC'22] Data Partition and Rate Control for Learning and Energy Efficient Edge Intelligence - [PDF]
• [TMC'22] Hastening Stream Offloading of Inference via Multi-exit DNNs in Mobile Edge Computing - [PDF]
• [TMC'22] EdgeAdaptor: Online Configuration Adaption, Model Selection and Resource Provisioning for Edge DNN Inference Serving at Scale - [PDF]
• [MobiSys'22] CoDL: efficient CPU-GPU co-execution for deep learning inference on mobile devices - [PDF]
• [MICRO'22] ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization - [PDF]
• [JSA'22] Edge intelligence in motion: Mobility-aware dynamic DNN inference service migration with downtime in mobile edge computing - [PDF]
• [JSA'22] Inference replication at edges via combinatorial multi-armed bandit - [PDF]
• [MobiCom'21] Elf: accelerate high-resolution mobile deep vision with content-aware parallel offloading - [PDF] [Code]

Serverless Computing

• [TSC'24] faasHouse: Sustainable Serverless Edge Computing through Energy-aware Resource Scheduling - [PDF]
• [WWW'24] DirectFaaS: A Clean-Slate Network Architecture for Efficient Serverless Chain Communications - [PDF]
• [INFOCOM'24] On Efficient Zygote Container Planning and Task Scheduling for Edge Native Application Acceleration - [PDF]
• [TMC'24] Taming Serverless Cold Start of Cloud Model Inference with Edge Computing - [PDF]
• [INFOCOM'23] Enabling age-aware big data analytics in serverless edge clouds - [PDF]
• [INFOCOM'23] Online Container Scheduling for Data-intensive Applications in Serverless Edge Computing - [PDF]
• [INFOCOM'23] On Efficient Zygote Container Planning toward Fast Function Startup in Serverless Edge Cloud - [PDF]
• [TPDS'21] Dependent function embedding for distributed serverless edge computing - [PDF] [Code]

Large Language Models (LLMs) / Small Language Models (SLMs)

• [arXiv'24] OpenELM: An Efficient Language Model Family with Open Training and Inference Framework - [PDF] [Code] [HuggingFace]
• [arXiv'24] FOX-1 TECHNICAL REPORT - [PDF] [HuggingFace]
• [arXiv'24] Tinyllama: An open-source small language model - [PDF] [Code]
• [arXiv'24] MobileVLM V2: Faster and Stronger Baseline for Vision Language Model - [PDF] [Code]
• [arXiv'24] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration - [PDF] [Code]
• [arXiv'24] MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases - [PDF]
• [arXiv'24] The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits - [PDF]
• [arXiv'24] Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone - [PDF]
• [arXiv'24] Exploring post-training quantization in llms from comprehensive study to low rank compensation - [PDF]
• [OSDI'24] ServerlessLLM: Low-Latency Serverless Inference for Large Language Models - [PDF] [Code]
• [EdgeFM'24] Large Language Models on Mobile Devices: Measurements, Analysis, and Insights - [PDF]
• [arXiv'24] vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving - [PDF]
• [arXiv'24] Toward Scalable Generative AI via Mixture of Experts in Mobile Edge Networks - [PDF]
• [EuroSys'23] Tabi: An Efficient Multi-Level Inference System for Large Language Models - [PDF]

Graph Processing/Scheduling

• [WWW'24] λGrapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing - [PDF]
• [TMC'24] Startup-aware Dependent Task Scheduling with Bandwidth Constraints in Edge Computing - [PDF]
• [ToN'24] Serving Graph Neural Networks With Distributed Fog Servers for Smart IoT Services - [PDF]
• [arXiv'24] Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems - [PDF]
• [TOSN'23] DAG Scheduling in Mobile Edge Computing - [PDF]
• [INFOCOM'23] Two-level Graph Caching for Expediting Distributed GNN Training - [PDF]
• [WWW'22] Fograph: Enabling real-time deep graph inference with fog computing - [PDF]

Optimization for Edge systems

• [WWW'24] MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment - [PDF]
• [INFOCOM'24] Online Resource Allocation for Edge Intelligence with Colocated Model Retraining and Inference - [PDF] [Code]
• [INFOCOM'24] EdgeTimer: Adaptive Multi-Timescale Scheduling in Mobile Edge Computing with Deep Reinforcement Learning - [PDF]
• [INFOCOM'24] In-Orbit Processing or Not? Sunlight-Aware Task Scheduling for Energy-Efficient Space Edge Computing Networks - [PDF]
• [INFOCOM'24] VeriEdge: Verifying and Enforcing Service Level Agreements for Pervasive Edge Computing - [PDF]
• [TMC'24] Joint task offloading and resource allocation in heterogeneous edge environments - [PDF]
• [TMC'24] Deep Learning-Assisted Online Task Offloading for Latency Minimization in Heterogeneous Mobile Edge - [PDF]
• [INFOCOM'23] FEAT: Towards Fast Environment-Adaptive Task Offloading and Power Allocation in MEC - [PDF]
• [INFOCOM'23] Latency-Optimal Pyramid-based Joint Communication and Computation Scheduling for Distributed Edge Computing - [PDF]
• [INFOCOM'23] Dynamic Edge-centric Resource Provisioning for Online and Offline Services Co-location - [PDF]
• [INFOCOM'23] Layered Structure Aware Dependent Microservice Placement Toward Cost Efficient Edge Clouds - [PDF]
• [INFOCOM'23] Latency-Optimal Pyramid-based Joint Communication and Computation Scheduling for Distributed Edge Computing - [PDF]
• [INFOCOM'23] AdaptSLAM: Edge-Assisted Adaptive SLAM with Resource Constraints via Uncertainty Minimization - [PDF] [Code]
• [JSAC'23] Dependent task scheduling and offloading for minimizing deadline violation ratio in mobile edge computing networks - [PDF]
• [TSC'23] Role-Based User Allocation Driven by Criticality in Edge Computing - [PDF]
• [TSC'23] Joint Optimization of Coverage and Reliability for Application Placement in Mobile Edge Computing - [PDF]
• [TPDS'23] CoopEdge+: Enabling Decentralized, Secure and Cooperative Multi-Access Edge Computing Based on Blockchain - [PDF]
• [TPDS'23] EESaver: Saving Energy Dynamically for Green Multi-Access Edge Computing - [PDF]
• [TPDS'23] ProScale: Proactive Autoscaling for Microservice With Time-Varying Workload at the Edge - [PDF]
• [TNSE'23] Re-Scheduling IoT Services in Edge Networks - [PDF]
• [TMC'23] OL-EUA: Online User Allocation for NOMA-Based Mobile Edge Computing - [PDF]
• [TMC'23] Multi-Agent Deep Reinforcement Learning Based UAV Trajectory Optimization for Differentiated Services - [PDF]
• [TMC'23] Lightweight Imitation Learning for Real-Time Cooperative Service Migration - [PDF]
• [IWQoS'23] OSCA: Online User-managed Server Selection and Configuration Adaptation for Interactive MAR - [PDF]
• [TSC'22] ST-EUA: Spatio-temporal Edge User Allocation with Task Decomposition - [PDF]
• [TPDS'22] Joint Application Placement and Request Routing Optimization for Dynamic Edge Computing Service Management - [PDF]
• [TMC'22] Online User and Power Allocation in Dynamic NOMA-Based Mobile Edge Computing - [PDF]
• [TMC'22] Price Competition in Multi-Server Edge Computing Networks under SAA and SIQ Models - [PDF]
• [IWQoS'22] An Online Approach for DNN Model Caching and Processor Allocation in Edge Computing - [PDF]
• [INFOCOM'22] Two Time-Scale Joint Service Caching and Task Offloading for UAV-assisted Mobile Edge Computing - [PDF]
• [INFOCOM'22] Online File Caching in Latency-Sensitive Systems with Delayed Hits and Bypassing - [PDF]
• [ICPP'22] Energy-efficient Edge Server Management for Edge Computing: A Game-theoretical Approach - [PDF]
• [CN'22] Adaptive provisioning for mobile cloud gaming at edges - [PDF]

Edge AI Systems

• [INFOCOM'24] Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference - [PDF]
• [INFOCOM'24] T-PRIME: Transformer-based Protocol Identification for Machine-learning at the Edge - [PDF]
• [INFOCOM'23] Tapfinger: Task placement and fine-grained resource allocation for edge machine learning - [PDF] [Code]
• [TCC'23] AI-Bazaar: A Cloud-Edge Computing Power Trading Framework for Ubiquitous AI Services - [PDF]
• [arXiv'23] Message Passing Meets Graph Neural Networks: A New Paradigm for Massive MIMO Systems - [PDF]
• [arXiv'23] Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks - [PDF]
• [WWW'22] Pyramid: Enabling Hierarchical Neural Networks with Edge Computing - [PDF]
• [JCIN'22] Resource-Constrained Edge AI with Early Exit Prediction - [PDF]
• [ICC'22] Loading Cost-Aware Model Caching and Request Routing for Cooperative Edge Inference - [PDF]

System-Level Analytics & Evaluation

• [INFOCOM'24] QM-RGNN: An Efficient Online QoS Measurement Framework with Sparse Matrix Imputation for Distributed Edge Clouds - [PDF]
• [WWW'24] PASS: Predictive Auto-Scaling System for Large-scale Enterprise Web Applications - [PDF]
• [KDD'23] One for All: Unified Workload Prediction for Dynamic Multi-tenant Edge Cloud Platforms - [PDF] [Code]
• [WWW'23] ELASTIC: Edge Workload Forecasting based on Collaborative Cloud-Edge Deep Learning - [PDF]
• [TKDE'23] A Measurement-Driven Analysis and Prediction of Content Propagation in the Device-to-Device Social Networks - [PDF]
• [IWQoS'23] How Far Have Edge Clouds Gone? A Spatial-Temporal Analysis of Edge Network Latency In the Wild - [PDF]
• [IWQoS'23] A Holistic QoS View of Crowdsourced Edge Cloud Platform - [PDF]
• [WWWJ'23] A large-scale holistic measurement of crowdsourced edge cloud platform - [PDF]
• [TMC'23] A Comprehensive Deep Learning Library Benchmark and Optimal Library Selection - [PDF]
• [WWW'22] Commutativity-guaranteed Docker Image Reconstruction towards Effective Layer Sharing - [PDF]
• [TMC'22] Fine-Grained Spatio-Temporal Distribution Prediction of Mobile Content Delivery in 5G Ultra-Dense Networks - [PDF]
• [arXiv'22] Benchmarking of DL Libraries and Models on Mobile Devices - [PDF]
• [arXiv'22] SoC-Cluster as an Edge Server: an Application-driven Measurement Study - [PDF]

Edge Security & Privacy

• [WWW'24] Poisoning Attack on Federated Knowledge Graph Embedding - [PDF] [Code]
• [WWW'24] GEES: Enabling Location Privacy-Preserving Energy Saving in Multi-Access Edge Computing - [PDF] [Code & Datasets]
• [TWC'23] Securing Large-Scale D2D Networks Using Covert Communication and Friendly Jamming - [PDF]
• [TMC'23] On the Robustness of Channel Allocation in Joint Radar and Communication Systems: An Auction Approach - [PDF]
• [ToN'23] Privacy Protection Under Incomplete Social and Data Correlation Information - [PDF]
• [KDD'23] Investigating Trojan Attacks on Pre-trained Language Model-powered Database Middleware - [PDF]
• [MobiCom'23] Enc2: Privacy-Preserving Inference for Tiny IoTs via Encoding and Encryption - [PDF]
• [INFOCOM'23] Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing - [PDF]

On-Device Intelligence

• [WWW'24] Towards Energy-efficient Federated Learning via INT8-based Training on Mobile DSPs - [PDF]
• [WWW'24] Cold Start or Hot Start? Robust Slow Start in Congestion Control with A Priori Knowledge for Mobile Web Services - [PDF]
• [INFOCOM'24] edgeSLAM2: Rethinking Edge-Assisted Visual SLAM with On-Chip Intelligence - [PDF]
• [INFOCOM'24] Minimizing Latency for Multi-DNN Inference on Resource-Limited CPU-Only Edge Devices - [PDF]
• [MobiSys'23] Boosting DNN Cold Inference on Edge Devices - [PDF] [Code]
• [MobiCom'23] SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices - [PDF] [Code]
• [TMC'23] AdaEvo: Edge-Assisted Continuous and Timely DNN Model Evolution for Mobile Devices - [PDF]
• [MWUT'23] DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing - [PDF]
• [MobiSys'23] NN-Stretch: Automatic Neural Network Branching for Parallel Inference on Heterogeneous Multi-Processors - [PDF]
• [MobiCom'23] AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments - [PDF]
• [MobiCom'23] LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup - [PDF]
• [MobiCom'23] Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios - [PDF]
• [MobiCom'23] Cost-effective On-device Continual Learning over Memory Hierarchy with Miro - [PDF]
• [arXiv'23] Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints - [PDF]
• [arXiv'23] Empowering LLM to use Smartphone for Intelligent Task Automation - [PDF]
• [SenSys'22] Hyperion: A Generic and Distributed Mobile Offloading Framework on OpenCL - [PDF]
• [MobiCom'22] MobiDepth: real-time depth estimation using on-device dual cameras - [PDF]

Video Analytics

• [INFOCOM'24] Gecko: Resource-Efficient and Accurate Queries in Real-Time Video Streams at the Edge - [PDF]
• [INFOCOM'24] Rosevin: Employing Resource- and Rate-Adaptive Edge Super-Resolution for Video Streaming - [PDF]
• [INFOCOM'24] Smart Data-Driven Proactive Push to Edge Network for User-Generated Videos - [PDF]
• [INFOCOM'24] BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge - [PDF]
• [WWW'24] NCTM: A Novel Coded Transmission Mechanism for Short Video Deliveries - [PDF]
• [MobiCom'23] AccuMO: Accuracy-centric multitask offloading in edge-assisted mobile augmented reality - [PDF] [Code]
• [MobiCom'23] NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras - [PDF]
• [INFOCOM'23] Who is the Rising Star? Demystifying the Promising Streamers in Crowdsourced Live Streaming - [PDF]
• [INFOCOM'23] ResMap: Exploiting Sparse Residual Feature Map for Accelerating Cross-Edge Video Analytics - [PDF] [Code]
• [INFOCOM'23] OmniSense: Towards Edge-Assisted Online Analytics for 360-Degree Videos - [PDF]
• [INFOCOM'23] Energy-Efficient 360-Degree Video Streaming on Multicore-Based Mobile Devices - [PDF]
• [INFOCOM'23] EAVS: Edge-assisted Adaptive Video Streaming with Fine-grained Serverless Pipelines - [PDF]
• [TMC'23] Live Migration of Video Analytics Applications in Edge Computing - [PDF]
• [TMC'23] EMS: Erasure-Coded Multi-Source Streaming for UHD Videos Within Cloud Native 5G Networks - [PDF]
• [INFOCOM'23] Crowd2: Multi-agent Bandit-based Dispatch for Video Analytics upon Crowdsourcing - [PDF]
• [arXiv'23] Low-complexity Deep Video Compression with A Distributed Coding Architecture - [PDF]
• [SECON'22] Focus! Provisioning Attention-aware Detection for Real-time On-device Video Analytics - [PDF]
• [ICC'22] Multi-server Multi-user Game at Edges for Heterogeneous Video Analytics - [PDF]

Edge Cahcing

• [INFOCOM'24] Exploiting Storage for Computing: Computation Reuse in Collaborative Edge Computing - [PDF]
• [TMC'24] FedCache: A Knowledge Cache-Driven Federated Learning Architecture for Personalized Edge Intelligence - [PDF]
• [INFOCOM'23] Economic Analysis of Joint Mobile Edge Caching and Peer Content Sharing - [PDF]
• [INFOCOM'23] Dynamic Regret of Randomized Online Service Caching in Edge Computing - [PDF]
• [TPDS'23] A Proactive On-Demand Content Placement Strategy in Edge Intelligent Gateways - [PDF]
• [TMC'23] Efficient Algorithms for Service Chaining in NFV-Enabled Satellite Edge Networks - [PDF]
• [JSAC'23] Federated Deep Reinforcement Learning for Recommendation-Enabled Edge Caching in Mobile Edge-Cloud Computing Networks - [PDF]
• [TMC'22] Near-Optimal and Collaborative Service Caching in Mobile Edge Clouds - [PDF]
• [TMC'22] Stable Service Caching in MECs of Hierarchical Service Markets with Uncertain Request Rates - [PDF]
• [IPCCC'22] Pricing in the Open Market of Crowdsourced Video Edge Caching: A Newcomer Perspective - [PDF]

Edge Data Storage/Analytics

• [TPDS'23] Enabling Balanced Data Deduplication in Mobile Edge Computing - [PDF]
• [SIGIR'23] EDIndex: Enabling Fast Data Queries in Edge Storage Systems - [PDF]
• [TSC'22] Data Caching Optimization With Fairness in Mobile Edge Computing - [PDF]
• [TSC'22] Cost-Effective Data Placement in Edge Storage Systems with Erasure Code - [PDF]
• [TPDS'22] CSEdge: Enabling Collaborative Edge Storage for Multi-Access Edge Computing Based on Blockchain - [PDF]
• [KDD'22] EdgeWatch: Collaborative Investigation of Data Integrity at the Edge based on Blockchain - [PDF]
• [ICPP'22] Formulating Interference-aware Data Delivery Strategies in Edge Storage Systems - [PDF]

Cloud-Edge Systems

• [INFOCOM'24] Cur-CoEdge: Curiosity-Driven Collaborative Request Scheduling in Edge-Cloud Systems - [PDF]
• [TSC'23] CompCube: A Space-Time-Request Resource Trading Framework for Edge-Cloud Service Market - [PDF]
• [ToN'23] Collaborative Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud Network - [PDF]
• [JSAC'23] EdgeMatrix: A Resource-Redefined Scheduling Framework for SLA-Guaranteed Multi-Tier Edge-Cloud Computing Systems - [PDF]

Services Provision

• [ToN'24] Mean Field Graph Based D2D Collaboration and Offloading Pricing in Mobile Edge Computing - [PDF]
• [INFOCOM'24] A Practical Near Optimal Deployment of Service Function Chains in Edge-to-Cloud Networks - [PDF]
• [INFOCOM'24] Joint Optimization of Model Deployment for Freshness-Sensitive Task Assignment in Edge Intelligence - [PDF]
• [TC'23] Stateful Serverless Application Placement in MEC With Function and State Dependencies - [PDF]
• [INFOCOM'23] Dynamic Edge-centric Resource Provisioning for Online and Offline Services Co-location - [PDF]
• [INFOCOM'23] Digital Twin-Enabled Service Satisfaction Enhancement in Edge Computing - [PDF]
• [TSC'22] Service Home Identification of Multiple-Source IoT Applications in Edge Computing - [PDF]
• [ToN'22] Near Optimal Learning-Driven Mechanisms for Stable NFV Markets in Multitier Cloud Networks - [PDF]
• [TMC'22] Digital Twin-Assisted, SFC-Enabled Service Provisioning in Mobile Edge Computing - [PDF]
• [TMC'22] Budget-Aware User Satisfaction Maximization on Service Provisioning in Mobile Edge Computing - [PDF]
• [MASS'22] SFC-Enabled Reliable Service Provisioning in Mobile Edge Computing via Digital Twins - [PDF]
• [INFOCOM'22] Schedule or Wait: Age-Minimization for IoT Big Data Processing in MEC via Online Learning - [PDF]

Sensing & Wireless Communications

• [TSC'23] RuleDRL: Reliability-Aware SFC Provisioning with Bounded Approximations in Dynamic Environments - [PDF]
• [ToN'23] Reinforcement Learning-Based Particle Swarm Optimization for End-to-End Traffic Scheduling in TSN-5G Networks - [PDF]
• [TCOMM'23] Mobility-Aware Proactive Flow Setup in Software-Defined Mobile Edge Networks - [PDF]
• [IWQoS'23] Optimizing Average AoI with Directional Charging for Wireless-Powered Network Edge - [PDF]
• [arXiv'22] Graph Neural Networks for Wireless Communications: From Theory to Practice - [PDF]
• [TMC'23] Decoupled Association with Rate Splitting Multiple Access in UAV-assisted Cellular Networks Using Multi-agent Deep Reinforcement Learning - [PDF]
• [TMC'23] Efficient Dynamic Distributed Resource Slicing in 6G Multi-Access Edge Computing Networks with Online ADMM and Message Passing Graph Neural Networks - [PDF]
• [JSAC'23] Task-Oriented Delay-Aware Multi-Tier Computing in Cell-Free Massive MIMO Systems - [PDF]
• [JSAC'23] AI-Generated Incentive Mechanism and Full-Duplex Semantic Communications for Information Sharing - [PDF]
• [JSAC'23] Semantic Communications for Wireless Sensing: RIS-aided Encoding and Self-supervised Decoding - [PDF]
• [arXiv'23] Task-Oriented Integrated Sensing, Computation and Communication for Wireless Edge AI - [PDF]
• [arXiv'23] Joint Activity-Delay Detection and Channel Estimation for Asynchronous Massive Random Access - [PDF]
• [TMC'22] Wireless powered mobile edge computing: Dynamic resource allocation and throughput maximization - [PDF]
• [TWC'22] Joint Sensing and Communication-Rate Control for Energy Efficient Mobile Crowd Sensing - [PDF]
• [MobiCom'22] Wirelessly powered integrated sensing and communication - [PDF]

Unmanned Aerial Vehicle (UAV)

• [INFOCOM'24] An Online Joint Optimization Approach for QoE Maximization in UAV-Enabled Mobile Edge Computing - [PDF]
• [WWW'24] Air-CAD: Edge-Assisted Multi-Drone Network for Real-time Crowd Anomaly Detection - [PDF]
• [TMC'24] Multi-agent deep reinforcement learning based uav trajectory optimization for differentiated services - [PDF]
• [ToN'24] Incentive Mechanisms for Online Task Offloading With Privacy-Preserving in UAV-Assisted Mobile Edge Computing - [PDF]
• [INFOCOM'23] WiSwarm: Age-of-Information-based Wireless Networking for Collaborative Teams of UAVs - [PDF]
• [INFOCOM'23] A2-UAV: Application-Aware Content and Network Optimization of Edge-Assisted UAV Systems - [PDF]

Mobile Crowdsensing

• [INFOCOM'24] Seer: Proactive Revenue-Aware Scheduling for Live Streaming Services in Crowdsourced Cloud-Edge Platforms - [PDF]
• [TMC'23] AoI-guaranteed Incentive Mechanism for Mobile Crowdsensing with Freshness Concerns - [PDF]
• [TMC'23] Incentive Mechanism for Spatial Crowdsourcing With Unknown Social-Aware Workers: A Three-Stage Stackelberg Game Approach - [PDF]
• [TMC'23] Crowdsourcing Upon Learning: Energy-Aware Dispatch With Guarantee for Video Analytics - [PDF]
• [INFOCOM'23] AoI-aware Incentive Mechanism for Mobile Crowdsensing using Stackelberg Game - [PDF]
• [TMC'22] Combination of Auction Theory and Multi-Armed Bandits: Model, Algorithm, and Application - [PDF]

Resource Allocation/Management

• [INFOCOM'24] INVAR: Inversion Aware Resource Provisioning and Workload Scheduling for Edge Computing - [PDF]
• [TWC'23] Elastic Resource Allocation for Coded Distributed Computing Over Heterogeneous Wireless Edge Networks - [PDF]
• [TMC'23] MetaSlicing: A Novel Resource Allocation Framework for Metaverse - [PDF]
• [TCOMM'23] QoE Analysis and Resource Allocation for Wireless Metaverse Services - [PDF]
• [JSAC'23] Attention-Aware Resource Allocation and QoE Analysis for Metaverse xURLLC Services - [PDF]

Over-the-air Computation

• [WCNC'23] Task-Oriented Over-the-Air Computation for Multi-Device Edge Split Inference - [PDF]
• [TWC'23] Task-Oriented Over-the-Air Computation for Multi-Device Edge AI - [PDF]
• [arXiv'23] Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference - [PDF]
• [JSAC'22] Distributed Over-the-air Computing for Fast Distributed Optimization: Beamforming Design and Convergence Analysis - [PDF]

Coded Distributed Computing

• [TWC'23] Elastic Resource Allocation for Coded Distributed Computing Over Heterogeneous Wireless Edge Networks - [PDF]
• [TMC'23] Resource Optimization for UAV-assisted Wireless Power Charging Enabled Hybrid Coded Edge Computing Network - [PDF]
• [TMC'22] Secure and Efficient Coded Multi-Access Edge Computing with Generalized Graph Neural Networks - [PDF]