mlsanityData to 14 Oct 2026

Revisiting Outage for Edge Inference Systems

arXiv 2504.03686 ↗First posted 22 Mar 2025cs.NI cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

One of the key missions of sixth-generation (6G) mobile networks is to deploy large-scale artificial intelligence (AI) models at the network edge to provide remote-inference services for edge devices. The resultant platform, known as edge inference, will support a wide range of Internet-of-Things applications, such as autonomous driving, industrial automation, and augmented reality. Given the mission-critical and time-sensitive nature of these tasks, it is essential to design edge inference systems that are both reliable and capable of meeting stringent end-to-end (E2E) latency constraints. Existing studies, which primarily focus on communication reliability as characterized by channel outage probability, may fail to guarantee E2E performance, specifically in terms of E2E inference accuracy and latency. To address this limitation, we propose a theoretical framework that introduces and mathematically characterizes the inference outage (InfOut) probability, which quantifies the likelihood that the E2E inference accuracy falls below a target threshold. Under an E2E latency constraint, this framework establishes a fundamental tradeoff between communication overhead (i.e., uploading more sensor observations) and inference reliability as quantified by the InfOut probability. To find a tractable way to optimize this tradeoff, we derive accurate surrogate functions for InfOut probability by applying a Gaussian approximation to the distribution of the received discriminant gain. Experimental results demonstrate the superiority of the proposed design over conventional communication-centric approaches in terms of E2E inference reliability.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 27 of its 67 references that are in the map. First posted on arXiv 22 Mar 2025.

Builds on

27 of 67 references.

References · 27

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  4. 2019Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computingcited by 152
  5. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 144
  6. 2020Who2com: Collaborative Perception via Learnable Handshake Communicationcited by 127
  7. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 95
  8. 2023Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunitiescited by 90
  9. 2023Split Learning in 6G Edge Networkscited by 68
  10. 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
  11. 2020Communication-Computation Trade-Off in Resource-Constrained Edge Inferencecited by 60
  12. 2019Dense Feature Aggregation and Pruning for RGBT Trackingcited by 40
15 more
  1. 2020Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computingcited by 39
  2. 2019Robustness of Neural Networks: A Probabilistic and Practical Approachcited by 38
  3. 2022Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AIcited by 33
  4. 2022Resource Allocation for Multiuser Edge Inference with Batching and Early Exiting (Extended Version)cited by 22
  5. 2022Task-Oriented Communications for NextG: End-to-End Deep Learning and AI Security Aspectscited by 20
  6. 2022Task-Oriented Over-the-Air Computation for Multi-Device Edge AIcited by 14
  7. 2023Task-oriented Explainable Semantic Communicationscited by 13
  8. 2023Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interferencecited by 9
  9. 2019Joint Power and Blocklength Optimization for URLLC in a Factory Automation Scenariocited by 8
  10. 2023Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators through Training with Right-Censored Gaussian Noisecited by 8
  11. 2024Space-ground Fluid AI for 6G Edge Intelligencecited by 8
  12. 2020Task-Based Analog-to-Digital Converterscited by 7
  13. 2023Over-the-Air Multi-View Pooling for Distributed Sensingcited by 7
  14. 2025Integrated Sensing and Edge AI: Realizing Intelligent Perception in 6Gcited by 6
  15. 2023Learning Resource Allocation Policy: Vertex-GNN or Edge-GNN?cited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networkscited by 3
  2. 2025Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneitycited by 2
  3. 2026Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edgecited by 0
  4. 2026Space Generative AI with Solar Energy Harvestingcited by 0
  5. 2026SpaceDiffusion: Over-the-Orbit Diffusion for Space Generate-and-Forward Communicationscited by 0