mlsanityData to 7 Oct 2026

Adaptive Neural Trees

arXiv 1807.06699 ↗First posted 17 Jul 2018cs.NE cs.CV cs.LGcited by 64

Not on the map. Why?

Abstract (arXiv)

Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures. We unite the two via adaptive neural trees (ANTs) that incorporates representation learning into edges, routing functions and leaf nodes of a decision tree, along with a backpropagation-based training algorithm that adaptively grows the architecture from primitive modules (e.g., convolutional layers). We demonstrate that, whilst achieving competitive performance on classification and regression datasets, ANTs benefit from (i) lightweight inference via conditional computation, (ii) hierarchical separation of features useful to the task e.g. learning meaningful class associations, such as separating natural vs. man-made objects, and (iii) a mechanism to adapt the architecture to the size and complexity of the training dataset.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 15; 2022: 12; 2023: 13; 2024: 11; 2025: 6; 2026: 6.

64 papers.

Sort:

By area:

  1. 2021Dynamic Neural Networks: A Surveycited by 405
  2. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 198
  3. 2023Adaptive Rotated Convolution for Rotated Object Detectioncited by 51
  4. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  5. 2022Proto2Proto: Can you recognize the car, the way I do?cited by 23
  6. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  7. 2021Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descentcited by 14
  8. 2022POETREE: Interpretable Policy Learning with Adaptive Decision Treescited by 14
  9. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  10. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  11. 2022Learning Interpretable, High-Performing Policies for Autonomous Drivingcited by 11
  12. 2023GradTree: Learning Axis-Aligned Decision Trees with Gradient Descentcited by 11
38 more
  1. 2023Tree Variational Autoencoderscited by 10
  2. 2021Dynamic Slimmable Denoising Networkcited by 9
  3. 2022A Survey of Neural Treescited by 7
  4. 20233VL: Using Trees to Improve Vision-Language Models' Interpretabilitycited by 7
  5. 2024Learning a Decision Tree Algorithm with Transformerscited by 6
  6. 2024Vanilla Gradient Descent for Oblique Decision Treescited by 6
  7. 2019Tree-gated Deep Mixture-of-Experts For Pose-robust Face Alignmentcited by 5
  8. 2021A Neural Tangent Kernel Perspective of Infinite Tree Ensemblescited by 4
  9. 2022Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Selection with Theoretical Guaranteescited by 4
  10. 2025From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networkscited by 4
  11. 2021Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimationcited by 3
  12. 2022Backpropagation Neural Treecited by 3
  13. 2022Flexible Modeling and Multitask Learning using Differentiable Tree Ensemblescited by 3
  14. 2023Contrastive Hierarchical Clusteringcited by 3
  15. 2023Memorization Capacity of Neural Networks with Conditional Computationcited by 3
  16. 2024Early-exit Convolutional Neural Networkscited by 3
  17. 2024From Logits to Hierarchies: Hierarchical Clustering made Simplecited by 3
  18. 2024Language Model as Visual Explainercited by 3
  19. 2022Analyzing Tree Architectures in Ensembles via Neural Tangent Kernelcited by 2
  20. 2023Harnessing the Power of Choices in Decision Tree Learningcited by 2
  21. 2024TreeDiffusion: Hierarchical Generative Clustering for Conditional Diffusioncited by 2
  22. 2025Learning Interpretable Differentiable Logic Networks for Tabular Regressioncited by 2
  23. 2021SONG: Self-Organizing Neural Graphscited by 1
  24. 2021Tree in Tree: from Decision Trees to Decision Graphscited by 1
  25. 2021Dynamic Parameterized Network for CTR Predictioncited by 1
  26. 2021Shrub Ensembles for Online Classificationcited by 1
  27. 2022Transition Matrix Representation of Trees with Transposed Convolutionscited by 1
  28. 2022A Hybrid Framework for Sequential Data Prediction with End-to-End Optimizationcited by 1
  29. 2022DecisioNet: A Binary-Tree Structured Neural Networkcited by 1
  30. 2024ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorizationcited by 1
  31. 2025Hierarchical Retrieval at Scale: Bridging Transparency and Efficiencycited by 1
  32. 2021Dive into Decision Trees and Forests: A Theoretical Demonstrationcited by 0
  33. 2021Learning spectro-temporal representations of complex sounds with parameterized neural networkscited by 0
  34. 2021Weakly Supervised Recovery of Semantic Attributescited by 0
  35. 2021Interpretable Mixture Density Estimation by use of Differentiable Tree-modulecited by 0
  36. 2021Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learningcited by 0
  37. 2021Learning Multi-Layered GBDT Via Back Propagationcited by 0
  38. 2023OF-AE: Oblique Forest AutoEncoderscited by 0

50 most cited of 64 All 64 (JSON)