Potluck: Cross-Application Approximate Deduplication for Computation-Intensive Mobile Applications

Emerging mobile applications, such as cognitive assistance and augmented reality (AR) based gaming, are increasingly computation-intensive and latency-sensitive, while running on resource-constrained devices. The standard approaches to addressing these involve either offloading to a cloud(let) or local system optimizations to speed up the computation, often trading off computation quality for low latency. Instead, we observe that these applications often operate on similar input data from the camera feed and share common processing components, both within the same (type of) applications and across different ones. Therefore, deduplicating processing across applications could deliver the best of both worlds. In this paper, we present Potluck, to achieve approximate deduplication. At the core of the system is a cache service that stores and shares processing results between applications and a set of algorithms to process the input data to maximize deduplication opportunities. This is implemented as a background service on Android. Extensive evaluation shows that Potluck can reduce the processing latency for our AR and vision workloads by a factor of 2.5 to 10.

• Publication year

  2018

• Venue

  International Conference on Architectural Support for Programming Languages and Operating Systems

• Publication date

  2018-03-19

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3173162.3173185
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Understanding Diverse Usage Patterns from Large-Scale Appstore-Service Profiles

  2017cited by this paper
• Joint Compression of Near-Duplicate Videos

  2017cited by this paper
• Lossless Compression of JPEG Coded Photo Collections

  2016cited by this paper
• LEO: scheduling sensor inference algorithms across heterogeneous mobile processors and network resources

  2016cited by this paper
• MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints

  2016cited by this paper
• FlashBack: Immersive Virtual Reality on Mobile Devices via Rendering Memoization

  2016cited by this paper
• TensorFlow: A system for large-scale machine learning

  2016cited by this paper
• SEeSAW - Similarity Exploiting Storage for Accelerating Analytics Workflows

  2016cited by this paper
• Deep Networks for Image Super-Resolution with Sparse Prior

  2015cited by this paper
• Outatime: Using Speculation to Enable Low-Latency Continuous Interaction for Mobile Cloud Gaming

  2015cited by this paper
• Starfish: Efficient Concurrency Support for Computer Vision Applications

  2015cited by this paper
• Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices

  2015cited by this paper
• Secure Deduplication of General Computations

  2015cited by this paper
• Doppelgänger: A cache for approximate computing

  2015cited by this paper
• The Design and Implementation of a Wireless Video Surveillance System

  2015cited by this paper
• DeepEdge: A multi-scale bifurcated deep network for top-down contour detection

  2014cited by this paper
• Towards wearable cognitive assistance

  2014cited by this paper
• Ultra high definition HEVC DASH data set

  2014cited by this paper
• Cyber Foraging: Bridging Mobile and Cloud Computing

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Nectar: Automatic Management of Data and Computation in Datacenters

  2010cited by this paper
• Diversity in smartphone usage

  2010cited by this paper
• DryadInc: Reusing Work in Large-scale Computations

  2009cited by this paper
• The Case for VM-Based Cloudlets in Mobile Computing

  2009cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper
• Real-time KD-tree construction on graphics hardware

  2008cited by this paper
• Experience with an Object Reputation System for Peer-to-Peer Filesharing

  2006cited by this paper
• Pedestrian Detection using Infrared images and Histograms of Oriented Gradients

  2006cited by this paper
• Machine Learning for High-Speed Corner Detection

  2006cited by this paper
• SURF: Speeded Up Robust Features

  2006influential reference
• Pedestrian detection for driving assistance systems: single-frame classification and system level performance

  2004cited by this paper
• Locality-sensitive hashing scheme based on p-stable distributions

  2004cited by this paper
• Distinctive Image Features from Scale-Invariant Keypoints

  2004cited by this paper
• Principal Component Analysis

  2003cited by this paper
• Principal Component Analysis

  2002cited by this paper
• Agile application-aware adaptation for mobility

  1997cited by this paper
• Plenoptic modeling: an image-based rendering system

  1995cited by this paper
• Efficient Color Histogram Indexing for Quadratic Form Distance Functions

  1995cited by this paper
• A Combined Corner and Edge Detector

  1988cited by this paper
• A fuzzy K-nearest neighbor algorithm

  1985cited by this paper
• Distance measures for speech recognition, psychological and instrumental

  1976cited by this paper

• Collaborative Processing for Multi-Tenant Inference on Memory-Constrained Edge TPUs

  2026cites this paper
• ACR: Adaptive Computation Reuse for Video Analytics in Collaborative Edge Computing

  2025cites this paper
• RedunCut: Measurement-Driven Sampling and Accuracy Performance Modeling for Low-Cost Live Video Analytics

  2025cites this paper
• An Extensive Analysis on Examining Several Data Deduplication Techniques in Cloud Computing

  2025cites this paper
• Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps

  2025cites this paper
• SimCache: Similarity Caching for Efficient VLM-based Scene Understanding

  2025influential citation
• IRIS: Unleashing ISP-Software Cooperation to Optimize the Machine Vision Pipeline

  2025cites this paper
• CCRSat: A Collaborative Computation Reuse Framework for Satellite Edge Computing Networks

  2025cites this paper
• A Distribution Agnostic Rank-Based Measure for Proximity Search

  2025cites this paper
• Adapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning

  2024cites this paper
• Exploiting Storage for Computing: Computation Reuse in Collaborative Edge Computing

  2024cites this paper
• Internet of Things for gaming: A review

  2024cites this paper
• Genie: Smart ROS-based Caching for Connected Autonomous Robots

  2024cites this paper
• ReStorEdge: An edge computing system with reuse semantics

  2024influential citation
• eScope: A Fine-Grained Power Prediction Mechanism for Mobile Applications

  2024cites this paper
• Deduplicator: When Computation Reuse Meets Load Balancing at the Network Edge

  2024cites this paper
• Design and Implementation of Deduplication on F2FS

  2024cites this paper
• MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations

  2023cites this paper
• Rethinking Mobile AI Ecosystem in the LLM Era

  2023cites this paper
• Transparent File Deduplication with Reduced Update Cost on Encryption Enabled Mobile Devices

  2023cites this paper
• Graft: Efficient Inference Serving for Hybrid Deep Learning With SLO Guarantees via DNN Re-Alignment

  2023cites this paper
• δLTA: Decoupling Camera Sampling from Processing to Avoid Redundant Computations in the Vision Pipeline

  2023cites this paper
• AccuMO: Accuracy-Centric Multitask Offloading in Edge-Assisted Mobile Augmented Reality

  2023cites this paper
• Mobile Foundation Model as Firmware

  2023cites this paper
• Service Caching and Computation Reuse Strategies at the Edge: A Survey

  2023influential citation
• LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup

  2023cites this paper
• Floo: automatic, lightweight memoization for faster mobile apps

  2022cites this paper
• Federated Learning and Proactive Computation Reuse at the Edge of Smart Homes

  2022cites this paper
• Matching-based Service Offloading for Compute-less Driven IoT Networks

  2022cites this paper
• GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge

  2022cites this paper
• Sommelier: Curating DNN Models for the Masses

  2022cites this paper
• ComAI: Enabling Lightweight, Collaborative Intelligence by Retrofitting Vision DNNs

  2022cites this paper
• HiTDL: High-Throughput Deep Learning Inference at the Hybrid Mobile Edge

  2022cites this paper
• InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inference

  2022influential citation
• InFi: end-to-end learnable input filter for resource-efficient mobile-centric inference

  2022cites this paper
• Exploiting Frame Similarity for Efficient Inference on Edge Devices

  2022influential citation
• Co-Cache: Inertial-Driven Infrastructure-less Collaborative Approximate Caching

  2022influential citation
• Visage: enabling timely analytics for drone imagery

  2021cites this paper
• Flexible high-resolution object detection on edge devices with tunable latency

  2021cites this paper
• GRADES: Gradient Descent for Similarity Caching

  2021cites this paper
• Content Placement in Networks of Similarity Caches

  2021cites this paper
• Ascent Similarity Caching With Approximate Indexes

  2021cites this paper
• Mistify: Automating DNN Model Porting for On-Device Inference at the Edge

  2021cites this paper
• OpenUVR: an Open-Source System Framework for Untethered Virtual Reality Applications

  2021cites this paper
• Many Models at the Edge: Scaling Deep Inference via Model-Level Caching

  2021cites this paper
• Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics

  2021cites this paper
• ProSPECT: Proactive Storage Using Provenance for Efficient Compute and Tiering

  2021cites this paper
• Efficiency in the Serverless Cloud Computing Paradigm: A Survey Study

  2021cites this paper
• The Promise and Challenges of Computation Deduplication and Reuse at the Network Edge

  2021influential citation
• Efficiency in the serverless cloud paradigm: A survey on the reusing and approximation aspects

  2021cites this paper
• Palleon: A Runtime System for Efficient Video Processing toward Dynamic Class Skew

  2021cites this paper
• Whispering: Joint Service Offloading and Computation Reuse in Cloud-Edge Networks

  2021cites this paper
• Store Edge Networked Data (SEND): A Data and Performance Driven Edge Storage Framework

  2021cites this paper
• Reservoir: Named Data for Pervasive Computation Reuse at the Network Edge

  2021cites this paper
• SODA: Similar 3D Object Detection Accelerator at Network Edge for Autonomous Driving

  2021cites this paper
• AÇAI: Ascent Similarity Caching with Approximate Indexes

  2021cites this paper
• CoxNet: A Computation Reuse Architecture at the Edge

  2021cites this paper
• A Network-based Compute Reuse Architecture for IoT Applications

  2021cites this paper
• How Far Can We Go in Compute-less Networking: Computation Correctness and Accuracy

  2021cites this paper
• Compute-Less Networking: Perspectives, Challenges, and Opportunities

  2020cites this paper
• Cost- and QoS-Efficient Serverless Cloud Computing

  2020cites this paper
• CHA: A Caching Framework for Home-based Voice Assistant Systems

  2020cites this paper
• ICedge: When Edge Computing Meets Information-Centric Networking

  2020cites this paper
• Continuous, Real-Time Object Detection on Mobile Devices without Offloading

  2020cites this paper
• Networked Cameras Are the New Big Data Clusters

  2019cites this paper
• SPEED: Accelerating Enclave Applications Via Secure Deduplication

  2019cites this paper
• Minotaur: Adapting Software Testing Techniques for Hardware Errors

  2019cites this paper
• Cross-Device Computation Coordination for Mobile Collocated Interactions with Wearables

  2019cites this paper
• SECS: Efficient Deep Stream Processing via Class Skew Dichotomy

  2018influential citation
• FoggyCache: Cross-Device Approximate Computation Reuse

  2018cites this paper
• Immersion on the Edge: A Cooperative Framework for Mobile Immersive Computing

  2018cites this paper
• DeepCache: Principled Cache for Mobile Deep Vision

  2017cites this paper
• the 21st

  year unknowncites this paper
• DigitalCommons@UNO DigitalCommons@UNO

  year unknowncites this paper