Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computing
Not on the map. Why?
Abstract (arXiv)
Deploying deep neural networks (DNNs) on resource-constrained mobile devices presents significant challenges, particularly in achieving real-time performance while simultaneously coping with limited computational resources and battery life. While Mobile Edge Computing (MEC) offers collaborative inference with GPU servers as a promising solution, existing approaches primarily rely on layer-wise model partitioning and undergo significant transmission bottlenecks caused by the sequential execution of DNN operations. To address this challenge, we present Intra-DP, a high-performance collaborative inference system optimized for DNN inference on MEC. Intra DP employs a novel parallel computing technique based on local operators (i.e., operators whose minimum unit input is not the entire input tensor, such as the convolution kernel). By decomposing their computations (operations) into several independent sub-operations and overlapping the computation and transmission of different sub-operations through parallel execution, Intra-DP mitigates transmission bottlenecks in MEC, achieving fast and energy-efficient inference. The evaluation demonstrates that Intra-DP reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines, without sacrificing accuracy.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 86 references that are in the map. First posted on arXiv 8 Jul 2025.
Builds on
45 of 86 references.
References · 45
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
- 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
- 2021Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LMcited by 632
- 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
- 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 316
- 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
- 2020SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloudcited by 112
- 2016Resnet in Resnet: Generalizing Residual Architecturescited by 110
33 more
- 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
- 2023Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunitiescited by 90
- 2023Split Learning in 6G Edge Networkscited by 68
- 2020CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devicescited by 67
- 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
- 2024Theory, Analysis, and Best Practices for Sigmoid Self-Attentioncited by 64
- 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 62
- 2021RegNet: Self-Regulated Network for Image Classificationcited by 44
- 2019Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirectcited by 41
- 2023FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networkscited by 38
- 2023Optimal Resource Allocation for U-Shaped Parallel Split Learningcited by 33
- 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 31
- 2021Auto-Split: A General Framework of Collaborative Edge-Cloud AIcited by 30
- 2024FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Datacited by 25
- 2024SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Frameworkcited by 21
- 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
- 2024IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengerscited by 20
- 2022On Optimizing the Communication of Model Parallelismcited by 19
- 2024MERIT: Multimodal Wearable Vital Sign Waveform Monitoringcited by 16
- 2020VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantizationcited by 15
- 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
- 2020Offloading Optimization in Edge Computing for Deep Learning Enabled Target Tracking by Internet-of-UAVscited by 14
- 2024SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensingcited by 14
- 2025Constructing 4D Radio Map in LEO Satellite Networks with Limited Samplescited by 13
- 2024Sums: Sniffing Unknown Multiband Signals under Low Sampling Ratescited by 12
- 2021RF-Based Human Activity Recognition Using Signal Adapted Convolutional Neural Networkcited by 11
- 2024LEO Satellite Networks Assisted Geo-distributed Data Processingcited by 10
- 2020Intelligent Task Offloading for Heterogeneous V2X Communicationscited by 8
- 2024Accelerating End-Cloud Collaborative Inference via Near Bubble-free Pipeline Optimizationcited by 7
- 2024AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environmentscited by 6
- 2025SigChord: Sniffing Wide Non-sparse Multiband Signals for Terrestrial and Non-terrestrial Wireless Networkscited by 3
- 2017Datacenter Traffic Control: Understanding Techniques and Trade-offscited by 1
- 2021Converged Reconfigurable Intelligent Surface and Mobile Edge Computing for Space Information Networkscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.