mlsanityData to 7 Oct 2026

CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices

arXiv 1708.08917 ↗First posted 29 Aug 2017cs.CV cs.AI cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning; 2) the increased training complexity; and 3) the lack of rigorous guarantee of compression ratio and inference accuracy. To overcome these limitations, this paper proposes CirCNN, a principled approach to represent weights and process neural networks using block-circulant matrices. CirCNN utilizes the Fast Fourier Transform (FFT)-based fast multiplication, simultaneously reducing the computational complexity (both in inference and training) from O(n2) to O(nlogn) and the storage complexity from O(n2) to O(n), with negligible accuracy loss. Compared to other approaches, CirCNN is distinct due to its mathematical rigor: it can converge to the same effectiveness as DNNs without compression. The CirCNN architecture, a universal DNN inference engine that can be implemented on various hardware/software platforms with configurable network architecture. To demonstrate the performance and energy efficiency, we test CirCNN in FPGA, ASIC and embedded processors. Our results show that CirCNN architecture achieves very high energy efficiency and performance with a small hardware footprint. Based on the FPGA implementation and ASIC synthesis results, CirCNN achieves 6-102X energy efficiency improvements compared with the best state-of-the-art results.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 5; 2023: 9; 2024: 6; 2025: 7; 2026: 6.

53 papers.

Sort:

By area:

  1. 2021Global Filter Networks for Image Classificationcited by 257
  2. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 76
  3. 2023Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMscited by 61
  4. 2021Teachers Do More Than Teach: Compressing Image-to-Image Modelscited by 37
  5. 2022Deep Fourier Up-Samplingcited by 27
  6. 2021Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attentioncited by 26
  7. 2023Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researcherscited by 25
  8. 2021L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimizationcited by 21
  9. 2022Towards Sparsification of Graph Neural Networkscited by 18
  10. 2021Binary Complex Neural Network Acceleration on FPGAcited by 14
  11. 2021A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learningcited by 13
  12. 2021BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matricescited by 11
38 more
  1. 2021FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Acceleratorcited by 10
  2. 2021Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AIcited by 10
  3. 2022A Secure and Efficient Federated Learning Framework for NLPcited by 9
  4. 2025MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Servingcited by 8
  5. 2021GST: Group-Sparse Training for Accelerating Deep Reinforcement Learningcited by 7
  6. 2023Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filteringcited by 6
  7. 2021Doping: A technique for efficient compression of LSTM models using sparse structured additive matricescited by 5
  8. 2022T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXitcited by 5
  9. 2021LightLayers: Parameter Efficient Dense and Convolutional Layers for Image Classificationcited by 4
  10. 2021unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generationcited by 4
  11. 2023SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Acceleratorscited by 4
  12. 2024Parameter-Efficient Fine-Tuning via Circular Convolutioncited by 4
  13. 2021RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imagingcited by 3
  14. 2021Towards Memory-Efficient Neural Networks via Multi-Level in situ Generationcited by 3
  15. 2021Enabling Fast Deep Learning on Tiny Energy-Harvesting IoT Devicescited by 3
  16. 2023Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentationcited by 3
  17. 2025Block Circulant Adapter for Large Language Modelscited by 3
  18. 2021How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architecturescited by 2
  19. 2025Hardware-Efficient Photonic Tensor Core: Accelerating Deep Neural Networks with Structured Compressioncited by 2
  20. 2025Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectorscited by 2
  21. 2022DNN Training Acceleration via Exploring GPGPU Friendly Sparsitycited by 1
  22. 2023Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Acceleratorscited by 1
  23. 2023Physics-aware Roughness Optimization for Diffractive Optical Neural Networkscited by 1
  24. 2023Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generationcited by 1
  25. 2024Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptationcited by 1
  26. 2025CDFlow: Building Invertible Layers with Circulant and Diagonal Matricescited by 1
  27. 2026ToTMNet: FFT-Accelerated Toeplitz Temporal Mixing Network for Lightweight Remote Photoplethysmographycited by 1
  28. 2021Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networkscited by 0
  29. 2021SPA-GCN: Efficient and Flexible GCN Accelerator with an Application for Graph Similarity Computationcited by 0
  30. 2023Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruningcited by 0
  31. 2024Compositional Kronecker Context Optimization for Vision-Language Modelscited by 0
  32. 2024Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface datacited by 0
  33. 2024Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Securitycited by 0
  34. 2024Flexible Coded Distributed Convolution Computing for Enhanced Straggler Resilience and Numerical Stability in Distributed CNNscited by 0
  35. 2025Efficient training for large-scale optical neural network using an evolutionary strategy and attention pruningcited by 0
  36. 2025Memory-Efficient Training with In-Place FFT Implementationcited by 0
  37. 2026EdgeLDR: Quaternion Low-Displacement Rank Neural Networks for Edge-Efficient Deep Learningcited by 0
  38. 2026Harnessing Photonics for Machine Intelligencecited by 0

50 most cited of 53 All 53 (JSON)