# Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States

arXiv: https://arxiv.org/abs/2603.03146 · HTML: https://mlsanity.com/paper/2603.03146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 54 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [Federated Learning via Over-the-Air Computation](https://mlsanity.com/paper/1812.11750/) (2018)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Communication-Efficient Edge AI: Algorithms and Systems](https://mlsanity.com/paper/2002.09668/) (2020)
- [Towards an Intelligent Edge: Wireless Communication Meets Machine Learning](https://mlsanity.com/paper/1809.00343/) (2018)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [Communication-Computation Trade-Off in Resource-Constrained Edge Inference](https://mlsanity.com/paper/2006.02166/) (2020)
- [von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification](https://mlsanity.com/paper/1706.04264/) (2017)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI](https://mlsanity.com/paper/2207.00969/) (2022)
- [Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference](https://mlsanity.com/paper/1907.04523/) (2019)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Resource Allocation for Multiuser Edge Inference with Batching and Early Exiting (Extended Version)](https://mlsanity.com/paper/2204.05223/) (2022)
- [Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference](https://mlsanity.com/paper/2105.13618/) (2021)
- [Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval](https://mlsanity.com/paper/1802.09662/) (2018)
- [Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach](https://mlsanity.com/paper/2406.02616/) (2024)
- [Resource-Constrained Edge AI with Early Exit Prediction](https://mlsanity.com/paper/2206.07269/) (2022)
- [Integrated Sensing and Edge AI: Realizing Intelligent Perception in 6G](https://mlsanity.com/paper/2501.06726/) (2025)
- [Energy-Efficient Edge Inference in Integrated Sensing, Communication, and Computation Networks](https://mlsanity.com/paper/2503.00298/) (2025)
- [PartialLoading: User Scheduling and Bandwidth Allocation for Parameter-sharing Edge Inference](https://mlsanity.com/paper/2503.22982/) (2025)
- [Communication Efficient Cooperative Edge AI via Event-Triggered Computation Offloading](https://mlsanity.com/paper/2501.02001/) (2025)
- [Parametric-Sensitivity Aware Retransmission for Efficient AI Downloading](https://mlsanity.com/paper/2602.13607/) (2026)

## Abstract (arXiv)

Integrated communication and computation (IC2) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC2 technologies is hindered by the lack of a tractable theoretical framework for characterizing end-to-end (E2E) inference performance. The metric is highly complicated as it needs to account for both channel distortion and artificial intelligence (AI) model architecture and computational complexity. In this work, we address this challenge by developing a tractable analytical model for E2E inference accuracy and leveraging it to design a channel-adaptive AI algorithm that maximizes inference throughput, referred to as the edge processing rate (EPR), under latency and accuracy constraints. Specifically, we consider an edge inference system in which a server deploys a backbone model with early exit, which enables flexible computational complexity, to perform inference on data features transmitted by a mobile device. The proposed accuracy model characterizes high-dimensional feature distributions in the angular domain using a Mixture of von Mises (MvM) distribution. This leads to a desired closed-form expression for inference accuracy as a function of quantization bit-width and model traversal depth, which represents channel distortion and computational complexity, respectively. Building upon this accuracy model, we formulate and solve the EPR maximization problem under joint latency and accuracy constraints, leading to a channel-adaptive AI algorithm that achieves full IC2 integration. The proposed algorithm jointly adapts transmit-side feature compression and receive-side model complexity according to channel conditions to maximize overall efficiency and inference throughput. Experimental results demonstrate its superior performance as compared with fixed-complexity counterparts.