mlsanityData to 7 Oct 2026

LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference

arXiv 2309.14331 ↗First posted 25 Sep 2023cs.LG cs.AI cs.CRcited by 26

Not on the map. Why?

Abstract (arXiv)

The growth of Graph Convolution Network (GCN) model sizes has revolutionized numerous applications, surpassing human performance in areas such as personal healthcare and financial systems. The deployment of GCNs in the cloud raises privacy concerns due to potential adversarial attacks on client data. To address security concerns, Privacy-Preserving Machine Learning (PPML) using Homomorphic Encryption (HE) secures sensitive client data. However, it introduces substantial computational overhead in practical applications. To tackle those challenges, we present LinGCN, a framework designed to reduce multiplication depth and optimize the performance of HE based GCN inference. LinGCN is structured around three key elements: (1) A differentiable structural linearization algorithm, complemented by a parameterized discrete indicator function, co-trained with model weights to meet the optimization goal. This strategy promotes fine-grained node-level non-linear location selection, resulting in a model with minimized multiplication depth. (2) A compact node-wise polynomial replacement policy with a second-order trainable activation function, steered towards superior convergence by a two-level distillation approach from an all-ReLU based teacher model. (3) an enhanced HE solution that enables finer-grained operator fusion for node-wise activation functions, further reducing multiplication level consumption in HE-based inference. Our experiments on the NTU-XVIEW skeleton joint dataset reveal that LinGCN excels in latency, accuracy, and scalability for homomorphically encrypted inference, outperforming solutions such as CryptoGCN. Remarkably, LinGCN achieves a 14.2x latency speedup relative to CryptoGCN, while preserving an inference accuracy of 75% and notably reducing multiplication depth.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 61 of its 97 references that are in the map. First posted on arXiv 25 Sep 2023.

Builds on

61 of 97 references.

References · 61

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2017Mask R-CNNcited by 7,259
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  6. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  7. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  8. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  9. 2019Deep Leakage from Gradientscited by 1,004
  10. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  11. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  12. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
38 more
  1. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  2. 2019Understanding Straight-Through Estimator in Training Activation Quantized Neural Netscited by 225
  3. 2019AliGraph: A Comprehensive Graph Neural Network Platformcited by 152
  4. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  5. 2022Brain Network Transformercited by 92
  6. 2022What Makes Convolutional Models Great on Long Sequence Modeling?cited by 86
  7. 2020Molecular graph generation with Graph Neural Networkscited by 79
  8. 2016Training Sparse Neural Networkscited by 73
  9. 2022FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generationcited by 66
  10. 2022Accelerating Dataset Distillation via Model Augmentationcited by 62
  11. 2018Low Latency Privacy Preserving Inferencecited by 57
  12. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  13. 2021DeepReDuce: ReLU Reduction for Fast Private Inferencecited by 50
  14. 2018Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learningcited by 47
  15. 2020CryptoNAS: Private Inference on a ReLU Budgetcited by 40
  16. 2020Against Membership Inference Attack: Pruning is All You Needcited by 32
  17. 2022Federated Contrastive Learning for Volumetric Medical Image Segmentationcited by 32
  18. 2022Selective Network Linearization for Efficient Private Inferencecited by 31
  19. 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
  20. 2021Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimizationcited by 27
  21. 2020Fast OSCAR and OWL Regression via Safe Screening Rulescited by 25
  22. 2022Towards Training Billion Parameter Graph Neural Networks for Atomic Simulationscited by 25
  23. 2020Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruningcited by 24
  24. 2023Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networkscited by 22
  25. 2021Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrastcited by 21
  26. 2021Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integrationcited by 21
  27. 2022Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learningcited by 21
  28. 2022The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devicescited by 21
  29. 2022A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipeliningcited by 21
  30. 2020Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devicescited by 19
  31. 2020On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networkscited by 19
  32. 2022Towards Sparsification of Graph Neural Networkscited by 18
  33. 20211xN Pattern for Pruning Convolutional Neural Networkscited by 16
  34. 2022Distributed Contrastive Learning for Medical Image Segmentationcited by 16
  35. 2021Decentralized Unsupervised Learning of Visual Representationscited by 15
  36. 2022Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-offcited by 15
  37. 2018TAPAS: Tricks to Accelerate (encrypted) Prediction As a Servicecited by 14
  38. 2021Generic Neural Architecture Search via Regressioncited by 14

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 19; 2025: 3; 2026: 2.

26 papers.

Sort:

  1. 2024SwitchTab: Switched Autoencoders Are Effective Tabular Learnerscited by 37
  2. 2023MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Trainingcited by 25
  3. 2024Optimizing Automated Picking Systems in Warehouse Robots Using Machine Learningcited by 19
  4. 2024Identification of Prognostic Biomarkers for Stage III Non-Small Cell Lung Carcinoma in Female Nonsmokers Using Machine Learningcited by 17
  5. 2024Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusioncited by 16
  6. 2024AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computingcited by 15
  7. 2024Cross-border Commodity Pricing Strategy Optimization via Mixed Neural Network for Time Series Analysiscited by 12
  8. 2024Deep Analysis of Time Series Data for Smart Grid Startup Strategies: A Transformer-LSTM-PSO Model Approachcited by 11
  9. 2024Graphical Structural Learning of rs-fMRI data in Heavy Smokerscited by 11
  10. 2024Advanced AI Framework for Enhanced Detection and Assessment of Abdominal Trauma: Integrating 3D Segmentation with 2D CNN and RNN Modelscited by 9
  11. 2024Advanced Payment Security System:XGBoost, LightGBM and SMOTE Integratedcited by 8
  12. 2024Recording Brain Activity While Listening to Music Using Wearable EEG Devices Combined with Bidirectional Long Short-Term Memory Networkscited by 8
14 more
  1. 2024EITNet: An IoT-Enhanced Framework for Real-Time Basketball Action Recognitioncited by 8
  2. 2024Real-time Monitoring of Lower Limb Movement Resistance Based on Deep Learningcited by 8
  3. 2024LTPNet Integration of Deep Learning and Environmental Decision Support Systems for Renewable Energy Demand Forecastingcited by 7
  4. 2024TRIZ Method for Urban Building Energy Optimization: GWO-SARIMA-LSTM Forecasting modelcited by 6
  5. 2024PristiQ: A Co-Design Framework for Preserving Data Security of Quantum Learning in the Cloudcited by 5
  6. 2023Edge-InversionNet: Enabling Efficient Inference of InversionNet on Edge Devicescited by 2
  7. 2024Data-Algorithm-Architecture Co-Optimization for Fair Neural Networks on Skin Lesion Datasetcited by 2
  8. 2024Key Information Retrieval to Classify the Unstructured Data Content of Preferential Trade Agreementscited by 1
  9. 2024Cardiovascular Disease Detection By Leveraging Semi-Supervised Learningcited by 0
  10. 2025DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruningcited by 0
  11. 2025Panther: A Cost-Effective Privacy-Preserving Framework for GNN Training and Inference Services in Cloud Environmentscited by 0
  12. 2025PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networkscited by 0
  13. 2026FEnc2: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encodingcited by 0
  14. 2026TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systemscited by 0