mlsanityData to 7 Oct 2026

Homological Neural Networks: A Sparse Architecture for Multivariate Complexity

arXiv 2306.15337 ↗First posted 27 Jun 2023cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

The rapid progress of Artificial Intelligence research came with the development of increasingly complex deep learning models, leading to growing challenges in terms of computational complexity, energy efficiency and interpretability. In this study, we apply advanced network-based information filtering techniques to design a novel deep neural network unit characterized by a sparse higher-order graphical architecture built over the homological structure of underlying data. We demonstrate its effectiveness in two application domains which are traditionally challenging for deep learning: tabular data and time series regression problems. Results demonstrate the advantages of this novel design which can tie or overcome the results of state-of-the-art machine learning and deep learning models using only a fraction of parameters.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 43 of its 73 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

43 of 73 references.

References · 43

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  3. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  4. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  5. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  6. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  7. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  8. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  9. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  10. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  11. 2021Tabular Data: Deep Learning is Not All You Needcited by 530
  12. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
31 more
  1. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  2. 2017Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Sciencecited by 325
  3. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  4. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  5. 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 220
  6. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 198
  7. 2018Discrimination-aware Channel Pruning for Deep Neural Networkscited by 171
  8. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 148
  9. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  10. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  11. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 122
  12. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  13. 2018Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layerscited by 112
  14. 2020Simplicial Neural Networkscited by 105
  15. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  16. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  17. 2019Theoretical Issues in Deep Networks: Approximation, Optimization and Generalizationcited by 72
  18. 2020PMLB v1.0: An open source dataset collection for benchmarking machine learning methodscited by 58
  19. 2016Pruning Convolutional Neural Networks for Resource Efficient Inferencecited by 47
  20. 2021Simplicial Convolutional Neural Networkscited by 40
  21. 2015Network Filtering for Big Data: Triangulated Maximally Filtered Graphcited by 17
  22. 2016Parsimonious modeling with Information Filtering Networkscited by 14
  23. 2020The Dual Information Bottleneckcited by 14
  24. 2018Exploring Linear Relationship in Feature Map Subspace for ConvNets Compressioncited by 11
  25. 2020Simplicial complexes: higher-order spectral dimension and dynamicscited by 9
  26. 2022Anatomy of a Stablecoin's failure: the Terra-Luna casecited by 9
  27. 2018SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Mannerscited by 7
  28. 2019Learning Clique Forestscited by 7
  29. 2020Topological regularization with information filtering networkscited by 6
  30. 2017Sparse causality network retrieval from short time seriescited by 4
  31. 2023Topological Feature Selectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2024HLOB -- Information Persistence and Structure in Limit Order Bookscited by 8
  2. 2024Deep Limit Order Book Forecastingcited by 7
  3. 2023Homological Convolutional Neural Networkscited by 4
  4. 2025Information Filtering Networks: Theoretical Foundations, Generative Methodologies, and Real-World Applicationscited by 1
  5. 2026Compositional Sparsity as an Inductive Bias for Neural Architecture Designcited by 0