mlsanityData to 7 Oct 2026

PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization

arXiv 2307.09488 ↗First posted 18 Jul 2023cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Accurate yet efficient Deep Neural Networks (DNNs) are in high demand, especially for applications that require their execution on constrained edge devices. Finding such DNNs in a reasonable time for new applications requires automated optimization pipelines since the huge space of hyper-parameter combinations is impossible to explore extensively by hand. In this work, we propose PLiNIO, an open-source library implementing a comprehensive set of state-of-the-art DNN design automation techniques, all based on lightweight gradient-based optimization, under a unified and user-friendly interface. With experiments on several edge-relevant tasks, we show that combining the various optimizations available in PLiNIO leads to rich sets of solutions that Pareto-dominate the considered baselines in terms of accuracy vs model size. Noteworthy, PLiNIO achieves up to 94.34% memory reduction for a <1% accuracy drop compared to a baseline architecture.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 18 Jul 2023.

Builds on

26 of 37 references.

References · 26

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  4. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  5. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  6. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  7. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 412
  8. 2019AutoML: A Survey of the State-of-the-Artcited by 388
  9. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  10. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
  11. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  12. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
14 more
  1. 2021MLPerf Tiny Benchmarkcited by 118
  2. 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 92
  3. 2020Rethinking Differentiable Search for Mixed-Precision Neural Networkscited by 79
  4. 2020μNAS: Constrained Neural Architecture Search for Microcontrollerscited by 54
  5. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  6. 2020Bringing AI To Edge: From Deep Learning's Perspectivecited by 24
  7. 2023A Practical Mixed Precision Algorithm for Post-Training Quantizationcited by 23
  8. 2021HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Searchcited by 20
  9. 2023Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edgecited by 15
  10. 2022Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognitioncited by 9
  11. 2022Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodescited by 9
  12. 2020VEGA: Towards an End-to-End Configurable AutoML Pipelinecited by 3
  13. 2023Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inferencecited by 3
  14. 2022Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 0; 2026: 3.

9 papers.

  1. 2024Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networkscited by 6
  2. 2024Adaptive Deep Learning for Efficient Visual Pose Estimation aboard Ultra-low-power Nano-dronescited by 4
  3. 2024Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearablescited by 2
  4. 2024HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrayscited by 1
  5. 2024Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-dronescited by 1
  6. 2024Optimizing DNN Inference on Multi-Accelerator SoCs at Training-timecited by 0
  7. 2026BlankSkip: Early-exit Object Detection onboard Nano-dronescited by 0
  8. 2026End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearablescited by 0
  9. 2026MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensorcited by 0