mlsanityData to 7 Oct 2026

The Future of Consumer Edge-AI Computing

arXiv 2210.10514 ↗First posted 19 Oct 2022cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

In the last decade, Deep Learning has rapidly infiltrated the consumer end, mainly thanks to hardware acceleration across devices. However, as we look towards the future, it is evident that isolated hardware will be insufficient. Increasingly complex AI tasks demand shared resources, cross-device collaboration, and multiple data types, all without compromising user privacy or quality of experience. To address this, we introduce a novel paradigm centered around EdgeAI-Hub devices, designed to reorganise and optimise compute resources and data access at the consumer edge. To this end, we lay a holistic foundation for the transition from on-device to Edge-AI serving systems in consumer environments, detailing their components, structure, challenges and opportunities.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 30 of its 57 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

30 of 57 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  8. 2019Machine Unlearningcited by 1,020
  9. 2017Federated Multi-Task Learningcited by 669
  10. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  11. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  12. 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrinkcited by 183
18 more
  1. 2017Distributed Deep Neural Networks over the Cloud, the Edge and End Devicescited by 119
  2. 2020SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloudcited by 109
  3. 2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directionscited by 74
  4. 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
  5. 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 57
  6. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  7. 2021CaPC Learning: Confidential and Private Collaborative Learningcited by 33
  8. 2020Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Acceleratorcited by 30
  9. 2020HAPI: Hardware-Aware Progressive Inferencecited by 30
  10. 2022Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-designcited by 29
  11. 2021Smart at what cost? Characterising Mobile Deep Neural Networks in the wildcited by 25
  12. 2019Federated Learning with Autotuned Communication-Efficient Secure Aggregationcited by 23
  13. 2019EmBench: Quantifying Performance Variations of Deep Neural Networks across Modern Commodity Devicescited by 21
  14. 2021Multi-Exit Semantic Segmentation Networkscited by 18
  15. 2018All One Needs to Know about Fog Computing and Related Edge Computing Paradigms: A Complete Surveycited by 14
  16. 2020CookGAN: Meal Image Synthesis from Ingredientscited by 14
  17. 2022Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learningcited by 13
  18. 2022Multi-DNN Accelerators for Next-Generation AI Systemscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 4; 2026: 1.

12 papers.

  1. 2024MELTing point: Mobile Evaluation of Language Transformerscited by 35
  2. 2023Maestro: Uncovering Low-Rank Structures via Trainable Decompositioncited by 8
  3. 2024Semantic Successive Refinement: A Generative AI-aided Semantic Communication Frameworkcited by 8
  4. 2025lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Modelscited by 4
  5. 2023MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edgecited by 3
  6. 2024FedAli: Personalized Federated Learning Alignment with Prototype Layers for Generalized Mobile Servicescited by 2
  7. 2025Smaller, Smarter, Closer: The Edge of Collaborative Generative AIcited by 2
  8. 2025DecoHD: Decomposed Hyperdimensional Classification under Extreme Memory Budgetscited by 2
  9. 2025AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networkscited by 1
  10. 2024Profiling AI Models: Towards Efficient Computation Offloading in Heterogeneous Edge AI Systemscited by 0
  11. 2024MultiTASC++: A Continuously Adaptive Scheduler for Edge-Based Multi-Device Cascade Inferencecited by 0
  12. 2026MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networkscited by 0