Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/xumengwei/Edge-AI-Paper-List


https://github.com/xumengwei/Edge-AI-Paper-List

Last synced: 22 days ago
JSON representation

Awesome Lists containing this project

README 

        
> :warning: This repository is not maintained actively. Checkout our [survey paper](https://arxiv.org/pdf/2401.08092.pdf) on efficient LLM and the corresponding [paper list](https://github.com/UbiquitousLearning/Efficient_Foundation_Model_Survey).



# Edge-AI-Paper-List



**Target venues**: system conferences (*OSDI/SOSP/ATC/EuroSys/ASPLOS*), network conferences (*NSDI/SIGCOMM*) and mobile conferences (*MobiCom/MobiSys/SenSys/UbiComp*).



We will keep maintaining this list :)



Note: Edge here refers to resource-constrained devices, not edge servers; AI here mostly refers to deep learning.



Attention: we are maintaining a dedicated paper list for [resource-efficient LLM algorithms/systems](https://github.com/UbiquitousLearning/Paper-list-resource-efficient-large-language-model).



## Smartphones



### 2023

[ASPLOS'23] [TelaMalloc: Efficient On-Chip Memory Allocation for Production Machine Learning Accelerators](https://dl.acm.org/doi/10.1145/3567955.3567961) 



### 2022



[MobiSys'22] [FabToys: Plush Toys with Large Arrays of Fabric-based Pressure Sensors to Enable Fine-grained Interaction Detection](https://dl.acm.org/doi/10.1145/3498361.3538931) 

[MobiSys'22] [Floo: Automatic, Lightweight Memoization for Faster Mobile Apps](https://doi.org/10.1145/3498361.3538929) 

[MobiCom'22] [A-Mash: Providing Single-App Illusion for Multi-App Use through User-centric UI Mashup](https://dl.acm.org/doi/10.1145/3495243.3560522) 

[MobiCom'22] [Tutti: Coupling 5G RAN and Edge Computing for Latency-critical Video Analytics](https://dl.acm.org/doi/abs/10.1145/3495243.3560538) 



### 2021

[MobiCom'21] [AsyMo: scalable and efficient deep-learning inference on asymmetric mobile CPUs](https://dl.acm.org/doi/10.1145/3447993.3448625) 

[MobiCom'21] [Elf: accelerate high-resolution mobile deep vision with content-aware parallel offloading](https://dl.acm.org/doi/10.1145/3447993.3448628) 

[MobiCom'21] [UltraSE: single-channel speech enhancement using ultrasound](https://dl.acm.org/doi/10.1145/3447993.3448626) 

[MobiCom'21] [Experience: a five-year retrospective of MobileInsight](https://dl.acm.org/doi/10.1145/3447993.3448138) 

[MobiCom'21] [LegoDNN: block-grained scaling of deep neural networks for mobile vision](https://dl.acm.org/doi/10.1145/3447993.3483249) 

[MobiSys'21] [Tap: an app framework for dynamically composable mobile systems](https://dl.acm.org/doi/10.1145/3458864.3467678) 

[MobiSys'21] [zTT: learning-based DVFS with zero thermal throttling for mobile devices](https://dl.acm.org/doi/10.1145/3458864.3468161) 

[ATC'21] [Octo: INT8 Training with Loss-aware Compensation and Backward Quantization for Tiny On-device Learning](https://www.usenix.org/conference/atc21/presentation/zhou-qihua) 



### 2020

[MobiCom'20] [Deep Learning Based Wireless Localization for Indoor Navigation](https://dl.acm.org/doi/pdf/10.1145/3372224.3380894) 

[MobiCom'20] [SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud](https://dl.acm.org/doi/pdf/10.1145/3372224.3419194) 

[MobiCom'20] [Heimdall: Mobile GPU Coordination Platform for Augmented Reality Applications](https://dl.acm.org/doi/pdf/10.1145/3372224.3419192) 

[MobiCom'20] [NEMO: Enabling Neural-enhanced Video Streaming on Commodity Mobile Devices](https://dl.acm.org/doi/pdf/10.1145/3372224.3419185) 

[MobiCom'20] [OnRL: Improving Mobile Video Telephony via Online Reinforcement Learning](https://dl.acm.org/doi/pdf/10.1145/3372224.3419186) 

[ASPLOS'20] [PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning](https://dl.acm.org/doi/pdf/10.1145/3373376.3378534) 

[MobiSys'20] [Deep Compressive Offloading: Speeding up Neural Network Inference by Trading Edge Computation for Network Latency](https://doi.org/10.1145/3384419.3430898)

[MobiSys'20] [Fast and scalable In-memory Deep Multitask Learning via Neural Weight Virtualization](https://doi.org/10.1145/3386901.3388947)

[MobiSys'20] [MDLdroidLite: A Release-and-inhibit Control Approach to Resource-efficient Deep Neural Networks on Mobile Devices](https://doi.org/10.1145/3384419.3430716)

[MobiSys'20] [RF-net: A Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition](https://doi.org/10.1145/3384419.3430735)

[SenSys'20] [MobiPose: real-time multi-person pose estimation on mobile devices](https://dl.acm.org/doi/abs/10.1145/3384419.3430726) 



### 2019 and before

[MobiCom'19] [RNN-Based Room Scale Hand Motion Tracking](https://dl.acm.org/doi/10.1145/3300061.3345439) 

[MobiCom'19] [MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors](https://dl.acm.org/doi/10.1145/3300061.3345455) 

[EuroSys'19] [µLayer: Low Latency On-Device Inference Using Cooperative Single-Layer Acceleration and Processor-Friendly Quantization](https://dl.acm.org/doi/pdf/10.1145/3302424.3303950) 

[SenSys'19] [DeepAPP: A Deep Reinforcement Learning Framework for Mobile Application Usage Prediction](https://doi.org/10.1145/3356250.3360038)

[MobiCom'18] [DeepCache: Principled Cache for Mobile Deep Vision](https://dl.acm.org/doi/10.1145/3241539.3241563) 

[MobiCom'18] [NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision](https://dl.acm.org/doi/10.1145/3241539.3241559) 

[MobiCom'18] [FoggyCache: Cross-Device Approximate Computation Reuse](https://dl.acm.org/doi/10.1145/3241539.3241557) 

[MobiSys'18][On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework](https://doi.org/10.1145/3210240.3210337)

[MobiSys'18][FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices](https://doi.org/10.1145/3274783.3274840)

[MobiSys'17] [Accelerating Mobile Audio Sensing Algorithms through On-Chip GPU Offloading](https://dl.acm.org/ft_gateway.cfm?id=3081358&ftid=1882661&dwn=1&CFID=39793162&CFTOKEN=15a0f3fc0be5d576-24EC57D1-9A17-7F75-7BEC8FD035518031) 

[MobiSys'17] [MobileDeepPill: A Small-Footprint Mobile Deep Learning System for Recognizing Unconstrained Pill Images](https://dl.acm.org/ft_gateway.cfm?id=3081336&ftid=1882628&dwn=1&CFID=39793162&CFTOKEN=15a0f3fc0be5d576-24EC57D1-9A17-7F75-7BEC8FD035518031) 

[MobiSys'17] [DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware](https://dl.acm.org/ft_gateway.cfm?id=3081359&ftid=1882636&dwn=1&CFID=39793162&CFTOKEN=15a0f3fc0be5d576-24EC57D1-9A17-7F75-7BEC8FD035518031) 

[MobiSys'17] [DeepMon: Building Mobile GPU Deep Learning Models for Continuous Vision Applications](https://dl.acm.org/ft_gateway.cfm?id=3081360&ftid=1882639&dwn=1&CFID=39793162&CFTOKEN=15a0f3fc0be5d576-24EC57D1-9A17-7F75-7BEC8FD035518031) 

[ASPLOS'17] [Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge](https://dl.acm.org/doi/10.1145/3037697.3037698) 

[Ubicomp'16] [SpotGarbage: Smartphone App to Detect Garbage Using Deep Learning](https://dl.acm.org/doi/pdf/10.1145/2971648.2971731) 

[Ubicomp'15] [DeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning](https://dl.acm.org/doi/pdf/10.1145/2750858.2804262) 



## AR/VR



[MobiCom'23] [AccuMO: Accuracy-Centric Multitask Offloading in Edge-Assisted Mobile Augmented Reality](https://dl.acm.org/doi/10.1145/3570361.3592531) 

[MobiCom'22] [SalientVR: saliency-driven mobile 360-degree video streaming with gaze information](https://dl.acm.org/doi/abs/10.1145/3495243.3517018) 

[MobiCom'21] [Face-Mic: inferring live speech and speaker identity via subtle facial dynamics captured by AR/VR motion sensors](https://dl.acm.org/doi/10.1145/3447993.3483272) 

[MobiSys'21] [Xihe: a 3D vision-based lighting estimation framework for mobile augmented reality](https://dl.acm.org/doi/10.1145/3458864.3467886) 

[MobiSys'21] [LensCap: split-process framework for fine-grained visual privacy control for augmented reality apps](https://dl.acm.org/doi/10.1145/3458864.3467676) 

[ASPLOS'20] [Coterie: Exploiting Frame Similarity to Enable High-Quality Multiplayer VR on Commodity Mobile Devices](https://dl.acm.org/doi/pdf/10.1145/3373376.3378516) 

[MobiCom'19] [Edge Assisted Real-time Object Detection for Mobile Augmented Reality](https://dl.acm.org/doi/10.1145/3300061.3300116) 

[EuroSys'19] [Transparent AR Processing Acceleration at the Edge](https://dl.acm.org/doi/pdf/10.1145/3301418.3313942) 

[ASPLOS'21] [Q-VR: System-Level Design for Future Collaborative Virtual Reality Rendering](https://dl.acm.org/doi/abs/10.1145/3445814.3446715) 

[ATC'20] [Firefly: Untethered Multi-user VR for Commodity Mobile Devices](https://www.usenix.org/conference/atc20/presentation/liu-xing) 



## IoTs



### 2023

[MobiCom'23] [Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios](https://dl.acm.org/doi/10.1145/3570361.3592514) 

[NSDI'23] [Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge](https://www.usenix.org/conference/nsdi23/presentation/padmanabhan) 

[ASPLOS'23] [Space-Efficient TREC for Enabling Deep Learning on Microcontrollers](https://dl.acm.org/doi/10.1145/3582016.3582062) 

[ASPLOS'23] [STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining](https://dl.acm.org/doi/10.1145/3575693.3575698) 

[ASPLOS'23] [HuffDuff: Stealing Pruned DNNs from Sparse Accelerators](https://dl.acm.org/doi/10.1145/3575693.3575738) 

[HPCA'23] [GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks](https://browse.arxiv.org/pdf/2203.00158.pdf) 

[HPCA'23] [Mix-GEMM: An efficient HW-SW Architecture for Mixed-Precision Quantized Deep Neural Networks Inference on Edge Devices](https://ieeexplore.ieee.org/document/10071076) 

[HPCA'23] [FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference](https://ieeexplore.ieee.org/document/10071015/) 

[ISCA'23] [Inter-layer Scheduling Space Definition and Exploration for Tiled Accelerators](https://dl.acm.org/doi/abs/10.1145/3579371.3589048) 



### 2022

[MobiSys'22] [TEO: Ephemeral Ownership for IoT Devices to Provide Granular Data Control](https://doi.org/10.1145/3498361.3539774) 

[MobiSys'22] [TinyNet: a Lightweight, Modular, and Unified Network Architecture for the Internet of Things](https://doi.org/10.1145/3498361.3538919) 

[MobiSys'22] [Bringing WebAssembly to Resource-constrained IoT Devices for Seamless Device-Cloud Integration](https://doi.org/10.1145/3498361.3538922) 

[MobiCom'22] [RetroIoT: Retrofitting Internet of Things Deployments by Hiding Data in Battery Readings](https://dl.acm.org/doi/abs/10.1145/3495243.3560536) 

[Mobisys'22] [DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets](https://dl.acm.org/doi/10.1145/3498361.3538945) 

[ATC'22] [CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics](https://www.usenix.org/system/files/atc22-hwang.pdf) 

[EuroSys'22] [LiteReconfig: Cost and Content Aware Reconfiguration of Video Object Detection Systems for Mobile GPUs](https://dl.acm.org/doi/pdf/10.1145/3492321.3519577) 

[SenSys'22] [AutoMatch: Leveraging Traffic Camera to Improve Perception and Localization of Autonomous Vehicles](https://yanzhenyu.com/assets/pdf/AutoMatch-SenSys22.pdf) 

[NeurIPS'22] [On-Device Training Under 256KB Memory](https://proceedings.neurips.cc/paper_files/paper/2022/file/90c56c77c6df45fc8e556a096b7a2b2e-Paper-Conference.pdf) 



### 2021

[ATC'21] [Video Analytics with Zero-streaming Cameras](https://xumengwei.github.io/files/ATC-DIVA.pdf)

[ATC'21] [Fine-tuning giant neural networks on commodity hardware with automatic pipeline model parallelism](https://www.usenix.org/conference/atc21/presentation/eliad) 

[ATC'21] [Palleon: A Runtime System for Efficient Video Processing toward Dynamic Class Skew](https://www.usenix.org/conference/atc21/presentation/feng-boyuan) 

[ASPLOS'21] [Rhythmic Pixel Regions: Visual sensing architecture for flexible spatiotemporal resolution towards high-precision visual computing at low power](https://dl.acm.org/doi/abs/10.1145/3445814.3446737) 

[NSDI'21] [AIRCODE: Hidden Screen-Camera Communication on an Invisible and Inaudible Dual Channel](https://www.usenix.org/conference/nsdi21/presentation/qian) 

[NSDI'21] [MAVL: Multiresolution Analysis of Voice Localization](https://www.usenix.org/conference/nsdi21/presentation/wang)



### 2020

[MobiSys'20] [Approximate Query Service on Autonomous IoT Cameras](https://xumengwei.github.io/files/MobiSys-Elf.pdf)

[MobiSys'20] [EMO: Real-time Emotion Recognition From Single-eye Images for Resource-constrained Eyewear Devices](https://doi.org/10.1145/3386901.3388917)

[MobiCom'20] [CLIO: Enabling Automatic Compilation of Deep Learning Pipelines Across IoT and Cloud](https://dl.acm.org/doi/pdf/10.1145/3372224.3419215) 

[MobiCom'20] [EagleEye: Wearable Camera-based Person Identification in Crowded Urban Spaces](https://dl.acm.org/doi/pdf/10.1145/3372224.3380881) 

[SigComm'20] [Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics](https://dl.acm.org/doi/pdf/10.1145/3387514.3405874) 

[EuroSys'20] [Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning](https://dl.acm.org/doi/abs/10.1145/3342195.3387555) 

[OSDI'20] [A Unified Architecture for Accelerating Distributed DNN Training in Heterogeneous GPU/CPU Clusters](https://www.usenix.org/conference/osdi20/presentation/jiang)

[OSDI'20] [PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications](https://www.usenix.org/conference/osdi20/presentation/bai)

[OSDI'20] [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://www.usenix.org/conference/osdi20/presentation/gujarati)



### 2019 and before

[MobiCom'19] [Source Compression with Bounded DNN Perception Loss for IoT Edge Computer Vision](https://dl.acm.org/doi/10.1145/3300061.3345448) 

[SenSys'19] [Neuro.ZERO: A Zero-energy Neural Network Accelerator for Embedded Sensing and Inference Systems](https://doi.org/10.1145/3356250.3360030)

[Ubicomp'19] [Performance Characterization of Deep Learning Models for Breathing-based Authentication on Resource-Constrained Devices](https://doi.org/10.1145/3287036)

[ASPLOS'18]  [SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing](https://dl.acm.org/doi/pdf/10.1145/3037697.3037746) 

[SenSys'17] [DeepIoT: Compressing Deep Neural Network Structures for Sensing Systems with a Compressor-Critic Framework](https://doi.org/10.1145/3131672.3131675)

[MobiSys'17] [Glimpse: A Programmable Early-Discard Camera Architecture for Continuous Mobile Vision](https://dl.acm.org/ft_gateway.cfm?id=3081347&ftid=1882638&dwn=1&CFID=39793162&CFTOKEN=15a0f3fc0be5d576-24EC57D1-9A17-7F75-7BEC8FD035518031) 

[Ubicomp'17] [Low-resource Multi-task Audio Sensing for Mobile and Embedded Devices via Shared Deep Neural Network Representations](https://dl.acm.org/doi/pdf/10.1145/3131895)

[MobiSys'16] [MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints](https://doi.org/10.1145/2906388.2906396)

[SenSys'16] [Sparsification and Separation of Deep Learning Layers for Constrained Resource Inference on Wearables](https://doi.org/10.1145/2994551.2994564)



## Energy-harvested devices



[MobiCom'23] [LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup](https://dl.acm.org/doi/10.1145/3570361.3613285) 

[MobiCom'23] [AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments](https://dl.acm.org/doi/10.1145/3570361.3592529) 

[MobiSys'20] [Approximate Query Service on Autonomous IoT Cameras](https://doi.org/10.1145/3386901.3388948)

[SenSys'20] [Ember: Energy Management of Batteryless Event Detection Sensors with Deep Reinforcement Learning](https://doi.org/10.1145/3384419.3430734)

[ASPLOS'19] [Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems](https://brandonlucia.com/pubs/2019.asplos.sonic.pdf) 

[ASPLOS'21] [Quantifying the Design-Space Tradeoffs in Autonomous Drones](https://dl.acm.org/doi/abs/10.1145/3445814.3446721) 

[ASPLOS'21] [Rhythmic Pixel Regions: Visual sensing architecture for flexible spatiotemporal resolution towards high-precision visual computing at low power](https://dl.acm.org/doi/abs/10.1145/3445814.3446737) 

[ATC'22] [PilotFish: Harvesting Free Cycles of Cloud Gaming with Deep Learning Training](https://www.usenix.org/system/files/atc22-choi-seungbeom.pdf)  



## Privacy&Security



### 2023

[MobiCom'23] [Efficient Federated Learning for Modern NLP](https://dl.acm.org/doi/10.1145/3570361.3592505) 

[MobiCom'23] [Federated Few-shot Learning for Mobile NLP](https://dl.acm.org/doi/10.1145/3570361.3613277) 

[MobiCom'23] [Enc2: Privacy-Preserving Inference for Tiny IoTs via Encoding and Encryption](https://dl.acm.org/doi/10.1145/3570361.3592501) 

[MobiCom'23] [AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving](https://dl.acm.org/doi/10.1145/3570361.3592517) 



### 2022

[MobiCom'22] [Audio-domain Position-independent Backdoor Attack via Unnoticeable Triggers](https://dl.acm.org/doi/10.1145/3495243.3560531) 

[MobiCom'22] [Sifter: Protecting Security-Critical Kernel Modules in Android through Attack Surface Reduction](https://dl.acm.org/doi/abs/10.1145/3495243.3560548) 

[ASPLOS'22] [Eavesdropping User Credentials via GPU Side Channels on Smartphones](https://dl.acm.org/doi/10.1145/3503222.3507757) 

[NSDI'22] [Privid: Practical, Privacy-Preserving Video Analytics Queries](https://www.usenix.org/system/files/nsdi22-paper-cangialosi.pdf) 

[EuroSys'22] [Minimum Viable Device Drivers for ARM TrustZone](https://dl.acm.org/doi/pdf/10.1145/3492321.3519565)  

[ATC'22] [PRIDWEN: Universally Hardening SGX Programs via Load-Time Synthesis](https://www.usenix.org/system/files/atc22-sang.pdf)  

[ATC'22] [HyperEnclave: An Open and Cross-platform Trusted Execution Environment](https://www.usenix.org/system/files/atc22-jia-yuekai.pdf)  

[OSDI'22] [BlackBox: A Container Security Monitor for Protecting Containers on Untrusted Operating Systems](https://www.usenix.org/system/files/osdi22-vant-hof.pdf) 

[OSDI'22] [Blockaid: Data Access Policy Enforcement for Web Applications](https://www.usenix.org/system/files/osdi22-zhang.pdf) 



### 2021

[MobiCom'21] [PECAM: privacy-enhanced video streaming and analytics via securely-reversible transformation](https://dl.acm.org/doi/10.1145/3447993.3448618) 

[MobiSys'21] [SafetyNOT: on the usage of the SafetyNet attestation API in Android](https://dl.acm.org/doi/10.1145/3458864.3466627) 

[MobiSys'21] [Rushmore: securely displaying static and animated images using TrustZone](https://dl.acm.org/doi/10.1145/3458864.3467887) 

[OSDI'21] [Privacy Budget Scheduling](https://www.usenix.org/system/files/osdi21-luo.pdf)

[OSDI'21] [Addra: Metadata-private voice communication over fully untrusted infrastructure](https://www.usenix.org/system/files/osdi21-ahmad.pdf)

[OSDI'21] [MAGE: Nearly Zero-Cost Virtual Memory for Secure Computation (Awarded Best Paper!)](https://www.usenix.org/system/files/osdi21-kumar.pdf)

[OSDI'21] [Zeph: Cryptographic Enforcement of End-to-End Data Privacy](https://www.usenix.org/system/files/osdi21-burkhalter.pdf)



### 2020 and before

[MobiCom'20] [FaceRevelio: A Face Liveness Detection System for Smartphones with A Single Front Camera](https://dl.acm.org/doi/pdf/10.1145/3372224.3419206) 

[ASPLOS'20] [DNNGuard: An Elastic Heterogeneous DNN Accelerator Architecture against Adversarial Attacks](https://dl.acm.org/doi/pdf/10.1145/3373376.3378532) 

[Ubicomp'20] [Countering Acoustic Adversarial Attacks in Microphone-equipped mart Home Devices](https://doi.org/10.1145/3397332)

[Ubicomp'19] [DeepType: On-Device Deep Learning for Input Personalization Service with Minimal Privacy Concern](https://doi.org/10.1145/3287075)

[Ubicomp'19] [Keyboard Snooping from Mobile Phone Arrays with Mixed Convolutional and Recurrent Neural Networks](https://doi.org/10.1145/3328916)

[MobiCom'19] [Occlumency: Privacy-preserving Remote Deep-learning Inference Using SGX](https://dl.acm.org/doi/10.1145/3300061.3345447) 

[EuroSys'19] [Forward and Backward Private Searchable Encryption with SGX](https://dl.acm.org/doi/pdf/10.1145/3301417.3312496)  

[SOSP'19] [Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform](https://dl.acm.org/doi/10.1145/3341301.3359639) 

[SOSP'19] [Honeycrisp: Large-scale Differentially Private Aggregation Without a Trusted Core](https://dl.acm.org/doi/10.1145/3341301.3359660) 

[SOSP'19] [Yodel: Strong Metadata Security for Voice Calls](https://dl.acm.org/doi/10.1145/3341301.3359648) 



## Learning



*Strikethrough indicates that these papers may have nothing to do with mobile* 



### 2023

[ICLR'23] [MocoSFL: enabling cross-client collaborative self-supervised learning](https://openreview.net/pdf?id=2QGJXyMNoPz) 

[EuroSys'23] [REFL: Resource-Efficient Federated Learning](https://dl.acm.org/doi/10.1145/3552326.3567485) 

[NSDI'23] [FLASH: Towards a High-performance Hardware Acceleration Architecture for Cross-silo Federated Learning](https://www.usenix.org/conference/nsdi23/presentation/zhang-junxue) 

[NSDI'23][RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics](https://www.usenix.org/conference/nsdi23/presentation/khani) 



### 2022

[MICRO'22] [GCD2: A Globally Optimizing Compiler for Mapping DNNs to Mobile DSPs](https://ieeexplore.ieee.org/document/9923837/) 

[MobiSys'22] [mGEMM: Low-latency Convolution with Minimal Memory Overhead Optimized for Mobile Devices](https://doi.org/10.1145/3498361.3538940) 

[MobiSys'22] [Band: Coordinated Multi-DNN Inference on Heterogeneous Mobile Processors](https://doi.org/10.1145/3498361.3538948) 

[MobiSys'22] [CoDL: Efficient CPU-GPU Co-execution for Deep Learning Inference on Mobile Devices](https://doi.org/10.1145/3498361.3538932) 

[MobiSys'22] [FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients](https://doi.org/10.1145/3498361.3538917) 

[MobiSys'22] [Memory-efficient DNN Training on Mobile Devices](https://doi.org/10.1145/3498361.3539765) 

[MobiSys'22] [Melon: Breaking the Memory Wall for Resource-Efficient On-Device Machine Learning](https://doi.org/10.1145/3498361.3538928) 

[MobiCom'22] [Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI](https://dl.acm.org/doi/abs/10.1145/3495243.3560551) 

[MobiCom'22] [Romou: Rapidly Generate High-Performance Tensor Kernels for Mobile GPUs](https://dl.acm.org/doi/abs/10.1145/3495243.3517020) 

[MobiCom'22] [InFi: end-to-end learnable input filter for resource-efficient mobile-centric inference](https://dl.acm.org/doi/abs/10.1145/3495243.3517016) 

[MobiCom'22] [PyramidFL: A Fine-grained Client Selection Framework for Efficient Federated Learning](https://dl.acm.org/doi/abs/10.1145/3495243.3517017) 

[MobiCom'22] [Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading](https://dl.acm.org/doi/abs/10.1145/3495243.3560545) 

[MobiCom'22] [NeuLens: Spatial-based Dynamic Acceleration of Convolutional Neural Networks on Edge](https://dl.acm.org/doi/10.1145/3495243.3560528) 

[MobiCom'22] [RF-URL: Unsupervised Representation Learning for RF Sensing](https://dl.acm.org/doi/10.1145/3495243.3560529) 

[MobiCom'22] [Cosmo: Contrastive Fusion Learning with Small Data for Multimodal Human Activity Recognition](https://dl.acm.org/doi/10.1145/3495243.3560519) 

[SenSys'22] [BlastNet: Exploiting Duo-Blocks for Cross-Processor Real-Time DNN Inference](https://yanzhenyu.com/assets/pdf/BlastNet-SenSys22.pdf) 

[SenSys'22] [PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference](https://arxiv.org/pdf/2211.06716v1.pdf) 

[UbiComp'22] [Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud](https://dl.acm.org/doi/10.1145/3494981) 

[OSDI'22] [Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning](https://www.usenix.org/system/files/osdi22-lv.pdf)

[ATC'22] [Campo: Cost-Aware Performance Optimization for Mixed-Precision Neural Network Training](https://www.usenix.org/system/files/atc22-he.pdf) 

[ATC'22] [SOTER: Guarding Black-box Inference for General Neural Networks at the Edge](https://www.usenix.org/system/files/atc22-shen.pdf) 

[EuroSys'22] [Varuna: Scalable, Low-cost Training of Massive Deep Learning Models (Best Paper Award)](https://dl.acm.org/doi/pdf/10.1145/3492321.3519584) 



### 2021

[MobiCom'21] [Hermes: an efficient federated learning framework for heterogeneous mobile clients](https://dl.acm.org/doi/10.1145/3447993.3483278) 

[MobiSys'21] [PPFL: privacy-preserving federated learning with trusted execution environments](https://dl.acm.org/doi/10.1145/3458864.3466628) 

[MobiSys'21] [ClusterFL: a similarity-aware federated learning system for human activity recognition](https://dl.acm.org/doi/10.1145/3458864.3467681) 

[MobiSys'21] [nn-Meter: towards accurate latency prediction of deep-learning model inference on diverse edge devices](https://dl.acm.org/doi/10.1145/3458864.3467882) 

[SenSys'21] [FedDL: Federated Learning via Dynamic Layer Sharing for Human Activity Recognition](https://dl.acm.org/doi/10.1145/3485730.3485946) 

[SenSys'21] [Mercury: Efficient On-Device Distributed DNN Training via Stochastic Importance Sampling](https://dl.acm.org/doi/10.1145/3485730.3485930) 

[SenSys'21] [FedMask: Joint Computation and Communication-Efficient Personalized Federated Learning via Heterogeneous Masking](https://dl.acm.org/doi/10.1145/3485730.3485929)  

[NSDI'21] [Mistify: Automating DNN Model Porting for On-Device Inference at the Edge](https://www.usenix.org/conference/nsdi21/presentation/guo)

[OSDI'21] [Oort: Efficient Federated Learning via Guided Participant Selection](https://www.usenix.org/system/files/osdi21-lai.pdf)

[ATC'21] [Jump-Starting Multivariate Time Series Anomaly Detection for Online Service Systems](https://www.usenix.org/conference/atc21/presentation/ma) 

[ATC'21] [Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training](https://www.usenix.org/conference/atc21/presentation/yu) 



### 2020 and before

[MobiCom'20] [Billion-scale Federated Learning on Mobile Clients: a submodel design with tunable privacy](https://dl.acm.org/doi/pdf/10.1145/3372224.3419188) 

[OSDI'20] [A Tensor Compiler for Unified Machine Learning Prediction Serving](https://www.usenix.org/conference/osdi20/presentation/nakandala)

[SenSys'19] [MetaSense: Few-shot Adaptation to Untrained Conditions in Deep Mobile Sensing](https://doi.org/10.1145/3356250.3360020)

[UbiComp'18] [DeepType: On-Device Deep Learning for Input Personalization Service with Minimal Privacy Concern](https://xumengwei.github.io/files/UbiComp-DeepType.pdf)



**Another awesome** [paper list about Federated Learning](https://github.com/chaoyanghe/Awesome-Federated-Learning)