mlsanityData to 7 Oct 2026

Exploring Randomly Wired Neural Networks for Image Recognition

arXiv 1904.01569 ↗First posted 2 Apr 2019cs.CV cs.LGcited by 103

Not on the map. Why?

Abstract (arXiv)

Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do this, we first define the concept of a stochastic network generator that encapsulates the entire network generation process. Encapsulation provides a unified view of NAS and randomly wired networks. Then, we use three classical random graph models to generate randomly wired graphs for networks. The results are surprising: several variants of these random generators yield network instances that have competitive accuracy on the ImageNet benchmark. These results suggest that new efforts focusing on designing better network generators may lead to new breakthroughs by exploring less constrained search spaces with more room for novel design.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 39; 2022: 21; 2023: 16; 2024: 11; 2025: 9; 2026: 6.

103 papers.

Sort:

By area:

  1. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  2. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  3. 2021Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Littlecited by 176
  4. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  5. 2021Learning Neural Network Subspacescited by 82
  6. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 71
  7. 2021Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Networkcited by 55
  8. 2023Graph Metanetworks for Processing Diverse Neural Architecturescited by 55
  9. 2023When Brain-inspired AI Meets AGIcited by 54
  10. 2023AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuningcited by 49
  11. 2021DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentationcited by 47
  12. 2022GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generationcited by 43
38 more
  1. 2021Automated Machine Learning on Graphs: A Surveycited by 38
  2. 2022Architectural Backdoors in Neural Networkscited by 24
  3. 2024Scale Equivariant Graph Metanetworkscited by 23
  4. 2021CATE: Computation-aware Neural Architecture Encoding with Transformerscited by 21
  5. 2021Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspectivecited by 19
  6. 2021Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligencecited by 18
  7. 2022On Redundancy and Diversity in Cell-based Neural Architecture Searchcited by 18
  8. 20211xN Pattern for Pruning Convolutional Neural Networkscited by 16
  9. 2022Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filterscited by 16
  10. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  11. 2024Graph Diffusion Policy Optimizationcited by 12
  12. 2021Exploring Robust Architectures for Deep Artificial Neural Networkscited by 11
  13. 2021T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imagingcited by 11
  14. 2022Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammarscited by 9
  15. 2022Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directionscited by 8
  16. 2022A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformerscited by 7
  17. 2022Improving Deep Neural Network Random Initialization Through Neuronal Rewiringcited by 7
  18. 2021Synthetic Data for Model Selectioncited by 6
  19. 2021SIAM: Chiplet-based Scalable In-Memory Acceleration with Mesh for Deep Neural Networkscited by 6
  20. 2021Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural Architecture Searchcited by 6
  21. 2021Approximate Neural Architecture Search via Operation Distribution Learningcited by 6
  22. 2021Dynamically Grown Generative Adversarial Networkscited by 5
  23. 2022FocusFormer: Focusing on What We Need via Architecture Samplercited by 5
  24. 2022GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Modelscited by 5
  25. 2025L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformerscited by 5
  26. 2021Bag of Tricks for Neural Architecture Searchcited by 4
  27. 2022Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysiscited by 4
  28. 2022Pareto-aware Neural Architecture Generation for Diverse Computational Budgetscited by 4
  29. 2024Principled Architecture-aware Scaling of Hyperparameterscited by 4
  30. 2021Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimizationcited by 3
  31. 2021Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgetscited by 3
  32. 2021RAN-GNNs: breaking the capacity limits of graph neural networkscited by 3
  33. 2021Adaptive Intermediate Representations for Video Understandingcited by 3
  34. 2021Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networkscited by 3
  35. 2021BNAS v2: Learning Architectures for Binary Networks with Empirical Improvementscited by 3
  36. 2021AUTOKD: Automatic Knowledge Distillation Into A Student Architecture Familycited by 3
  37. 2022Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Searchcited by 3
  38. 2023Beyond Multilayer Perceptrons: Investigating Complex Topologies in Neural Networkscited by 3

50 most cited of 103 All 103 (JSON)