mlsanityData to 7 Oct 2026

Deep Forest

arXiv 1702.08835 ↗First posted 28 Feb 2017cs.LG stat.MLcited by 46

Not on the map. Why?

Abstract (arXiv)

Current deep learning models are mostly build upon neural networks, i.e., multiple layers of parameterized differentiable nonlinear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules. We conjecture that the mystery behind the success of deep neural networks owes much to three characteristics, i.e., layer-by-layer processing, in-model feature transformation and sufficient model complexity. We propose the gcForest approach, which generates textitdeep forest holding these characteristics. This is a decision tree ensemble approach, with much less hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to get excellent performance by using the same default setting. This study opens the door of deep learning based on non-differentiable modules, and exhibits the possibility of constructing deep models without using backpropagation.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 5; 2024: 5; 2025: 11; 2026: 1.

46 papers.

Sort:

By area:

  1. 2021Ensemble deep learning: A reviewcited by 283
  2. 2023Deep Model Fusion: A Surveycited by 89
  3. 2021Boost then Convolve: Gradient Boosting Meets Graph Neural Networkscited by 42
  4. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  5. 2022Random vector functional link network: recent developments, applications, and future directionscited by 33
  6. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  7. 2021PyTorch Tabular: A Framework for Deep Learning with Tabular Datacited by 20
  8. 2022Attention-based Random Forest and Contamination Modelcited by 10
  9. 2021When are Deep Networks really better than Decision Forests at small sample sizes, and how?cited by 6
  10. 2024Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifierscited by 6
  11. 2022AGBoost: Attention-based Modification of Gradient Boosting Machinecited by 5
  12. 2023SSL-SoilNet: A Hybrid Transformer-based Framework with Self-Supervised Learning for Large-scale Soil Organic Carbon Predictioncited by 5
34 more
  1. 2023Inference with Mondrian Random Forestscited by 5
  2. 2021Visualizing Ensemble Predictions of Music Moodcited by 4
  3. 2022Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classificationcited by 4
  4. 2021Rheumatoid Arthritis: Automated Scoring of Radiographic Joint Damagecited by 3
  5. 2022Deep Forest with Hashing Screening and Window Screeningcited by 3
  6. 2025MVAN: Multi-View Attention Networks for Fake News Detection on Social Mediacited by 3
  7. 2025Spiking Manifestocited by 3
  8. 2021DBC-Forest: Deep forest with binning confidence screeningcited by 2
  9. 2022Online Deep Learning from Doubly-Streaming Datacited by 2
  10. 2022A Review of Modern Approaches for Coronary Angiography Imaging Analysiscited by 2
  11. 2025A topology-preserving three-stage framework for fully-connected coronary artery extractioncited by 2
  12. 2025Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboardcited by 2
  13. 2026PeroMAS: A Multi-agent System of Perovskite Material Discoverycited by 2
  14. 2021Efficient Click-Through Rate Prediction for Developing Countries via Tabular Learningcited by 1
  15. 2021Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuningcited by 1
  16. 2021Deep convolutional forest: a dynamic deep ensemble approach for spam detection in textcited by 1
  17. 2022Random Ferns for Semantic Segmentation of PolSAR Imagescited by 1
  18. 2022Sparse tree-based initialization for neural networkscited by 1
  19. 2022One Venue, Two Conferences: The Separation of Chinese and American Citation Networkscited by 1
  20. 2022Construction of a Surrogate Model: Multivariate Time Series Prediction with a Hybrid Modelcited by 1
  21. 2023Interpreting Deep Forest through Feature Contribution and MDI Feature Importancecited by 1
  22. 2024Automated Machine Learning for Positive-Unlabelled Learningcited by 1
  23. 2024Classical Machine Learning: Seventy Years of Algorithmic Learning Evolutioncited by 1
  24. 2024RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifierscited by 1
  25. 2025Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Modelscited by 1
  26. 2025Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learningcited by 1
  27. 2022Graph-incorporated Latent Factor Analysis for High-dimensional and Sparse Matricescited by 0
  28. 2022An Efficient FPGA-based Accelerator for Deep Forestcited by 0
  29. 2023Human Behavior in the Time of COVID-19: Learning from Big Datacited by 0
  30. 2024The Role of Depth, Width, and Tree Size in Expressiveness of Deep Forestcited by 0
  31. 2025Option Pricing Using Ensemble Learningcited by 0
  32. 2025Network Threat Detection: Addressing Class Imbalanced Data with Deep Forestcited by 0
  33. 2025RocketStack: Level-aware Deep Recursive Ensemble Learning Architecturecited by 0
  34. 2025TreeNet: Layered Decision Ensemblescited by 0