mlsanityData to 14 Oct 2026

The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices

arXiv 2202.11317 ↗First posted 23 Feb 2022cs.LG cs.CYcited by 21

Not on the map. Why?

Abstract (arXiv)

Along with the progress of AI democratization, neural networks are being deployed more frequently in edge devices for a wide range of applications. Fairness concerns gradually emerge in many applications, such as face recognition and mobile medical. One fundamental question arises: what will be the fairest neural architecture for edge devices? By examining the existing neural networks, we observe that larger networks typically are fairer. But, edge devices call for smaller neural architectures to meet hardware specifications. To address this challenge, this work proposes a novel Fairness- and Hardware-aware Neural architecture search framework, namely FaHaNa. Coupled with a model freezing approach, FaHaNa can efficiently search for neural networks with balanced fairness and accuracy, while guaranteed to meet hardware specifications. Results show that FaHaNa can identify a series of neural networks with higher fairness and accuracy on a dermatology dataset. Target edge devices, FaHaNa finds a neural architecture with slightly higher accuracy, 5.28x smaller size, 15.14% higher fairness score, compared with MobileNetV2; meanwhile, on Raspberry PI and Odroid XU-4, it achieves 5.75x and 5.79x speedup.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 22 of its 43 references that are in the map. First posted on arXiv 23 Feb 2022.

Builds on

22 of 43 references.

References · 22

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  3. 2019Searching for MobileNetV3cited by 1,994
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  6. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  7. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  8. 2019Fair Generative Modeling via Weak Supervisioncited by 114
  9. 2016Resnet in Resnet: Generalizing Residual Architecturescited by 110
  10. 2019Hardware/Software Co-Exploration of Neural Architecturescited by 50
  11. 2019FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edgecited by 48
  12. 2020Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Taskscited by 43
10 more
  1. 2019Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Searchcited by 38
  2. 2019Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Acceleratorscited by 32
  3. 2020Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Startcited by 22
  4. 2022Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learningcited by 21
  5. 2019On Neural Architecture Search for Resource-Constrained Hardware Platformscited by 18
  6. 2020MS-NAS: Multi-Scale Neural Architecture Search for Medical Image Segmentationcited by 16
  7. 2019Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inferencecited by 13
  8. 2021Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devicescited by 9
  9. 2020NASS: Optimizing Secure Inference via Neural Architecture Searchcited by 7
  10. 2021Optimizing FPGA-based Accelerator Design for Large-Scale Molecular Similarity Searchcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 7; 2025: 3; 2026: 1.

21 papers.

Sort:

By area:

  1. 2025Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Modelscited by 46
  2. 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
  3. 2023LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inferencecited by 27
  4. 2023Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networkscited by 22
  5. 2022Computing-In-Memory Neural Network Accelerators for Safety-Critical Systems: Can Small Device Variations Be Disastrous?cited by 12
  6. 2023Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platformscited by 12
  7. 2023On-Device Unsupervised Image Segmentationcited by 10
  8. 2024FL-NAS: Towards Fairness of NAS for Resource Constrained Devices via Large Language Modelscited by 9
  9. 2023Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Modelscited by 8
  10. 2023(Un)fair devices: Moving beyond AI accuracy in personal sensingcited by 6
  11. 2024FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Modelscited by 5
  12. 2023Compute-in-Memory based Neural Network Accelerators for Safety-Critical Systems: Worst-Case Scenarios and Protectionscited by 3
9 more
  1. 2024A Physics-guided Generative AI Toolkit for Geophysical Monitoringcited by 2
  2. 2024Data-Algorithm-Architecture Co-Optimization for Fair Neural Networks on Skin Lesion Datasetcited by 2
  3. 2025MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networkscited by 2
  4. 2024vMCU: Coordinated Memory Management and Kernel Optimization for DNN Inference on MCUscited by 1
  5. 2023U-SWIM: Universal Selective Write-Verify for Computing-in-Memory Neural Acceleratorscited by 0
  6. 2024Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Spacecited by 0
  7. 2024HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devicescited by 0
  8. 2025GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Searchcited by 0
  9. 2026FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deploymentcited by 0