mlsanityData to 7 Oct 2026

Hyperbolic Binary Neural Network

arXiv 2501.03471 ↗First posted 7 Jan 2025cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Binary Neural Network (BNN) converts full-precision weights and activations into their extreme 1-bit counterparts, making it particularly suitable for deployment on lightweight mobile devices. While binary neural networks are typically formulated as a constrained optimization problem and optimized in the binarized space, general neural networks are formulated as an unconstrained optimization problem and optimized in the continuous space. This paper introduces the Hyperbolic Binary Neural Network (HBNN) by leveraging the framework of hyperbolic geometry to optimize the constrained problem. Specifically, we transform the constrained problem in hyperbolic space into an unconstrained one in Euclidean space using the Riemannian exponential map. On the other hand, we also propose the Exponential Parametrization Cluster (EPC) method, which, compared to the Riemannian exponential map, shrinks the segment domain based on a diffeomorphism. This approach increases the probability of weight flips, thereby maximizing the information gain in BNNs. Experimental results on CIFAR10, CIFAR100, and ImageNet classification datasets with VGGsmall, ResNet18, and ResNet34 models illustrate the superior performance of our HBNN over state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 7 Jan 2025.

Builds on

43 of 55 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  7. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  8. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  9. 2014Convex Optimization: Algorithms and Complexitycited by 569
  10. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  11. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  12. 2018Hyperbolic Neural Networkscited by 393
31 more
  1. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  2. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 291
  3. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  4. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  5. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 160
  6. 2017Towards Accurate Binary Convolutional Neural Networkcited by 148
  7. 2018Scalable Methods for 8-bit Training of Neural Networkscited by 139
  8. 2019Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Groupcited by 133
  9. 2019XNOR-Net++: Improved Binary Neural Networkscited by 94
  10. 2017Orthogonal Recurrent Neural Networks with Scaled Cayley Transformcited by 82
  11. 2019Trivializations for Gradient-Based Optimization on Manifoldscited by 78
  12. 2020Rotated Binary Neural Networkcited by 77
  13. 2019Global Sparse Momentum SGD for Pruning Very Deep Neural Networkscited by 70
  14. 2019Regularizing Activation Distribution for Training Binarized Deep Networkscited by 61
  15. 2019Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimizationcited by 58
  16. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 51
  17. 2020Searching for Low-Bit Weights in Quantized Neural Networkscited by 43
  18. 2018Bi-Real Net: Binarizing Deep Network Towards Real-Network Performancecited by 42
  19. 2020Training Binary Neural Networks through Learning with Noisy Supervisioncited by 39
  20. 2021Learning Frequency Domain Approximation for Binary Neural Networkscited by 38
  21. 2020Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Frameworkcited by 27
  22. 2023Unified Data-Free Compression: Pruning and Quantization without Fine-Tuningcited by 22
  23. 2023Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Trainingcited by 19
  24. 2019Mirror Descent View for Neural Network Quantizationcited by 15
  25. 2023Resilient Binary Neural Networkcited by 13
  26. 2022Network Binarization via Contrastive Learningcited by 12
  27. 2020A Learning Framework for n-bit Quantized Neural Networks toward FPGAscited by 11
  28. 2023Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuningcited by 9
  29. 2023Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifoldcited by 7
  30. 2023Learning Discretized Neural Networks under Ricci Flowcited by 4
  31. 2020Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networkscited by 1

Built on by

Not cited yet.