mlsanityData to 7 Oct 2026

Multiple Instance Learning with Trainable Decision Tree Ensembles

arXiv 2302.06601 ↗First posted 13 Feb 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

A new random forest based model for solving the Multiple Instance Learning (MIL) problem under small tabular data, called Soft Tree Ensemble MIL (STE-MIL), is proposed. A new type of soft decision trees is considered, which is similar to the well-known soft oblique trees, but with a smaller number of trainable parameters. In order to train the trees, it is proposed to convert them into neural networks of a specific form, which approximate the tree functions. It is also proposed to aggregate the instance and bag embeddings (output vectors) by using the attention mechanism. The whole STE-MIL model, including soft decision trees, neural networks, the attention mechanism and a classifier, is trained in an end-to-end manner. Numerical experiments with tabular datasets illustrate STE-MIL. The corresponding code implementing the model is publicly available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 65 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

22 of 65 references.

References · 22

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  3. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  4. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  5. 2017Distilling a Neural Network Into a Soft Decision Treecited by 230
  6. 2018Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysiscited by 178
  7. 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
  8. 2019Deep neural network models for computational histopathology: A surveycited by 165
  9. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 163
  10. 2016Revisiting Multiple Instance Neural Networkscited by 119
  11. 2020The Tree Ensemble Layer: Differentiability meets Conditional Computationcited by 57
  12. 2015Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learningcited by 38
10 more
  1. 2019Resolving challenges in deep learning-based analyses of histopathological images using explanation methodscited by 32
  2. 2021MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Imagescited by 15
  3. 2019Oblique Decision Trees from Derivatives of ReLU Networkscited by 14
  4. 2021Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descentcited by 14
  5. 2015HHCART: An Oblique Decision Treecited by 13
  6. 2022Treeformer: Dense Gradient Trees for Efficient Attention Computationcited by 8
  7. 2023Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learningcited by 8
  8. 2021Nested Multiple Instance Learning with Attention Mechanismscited by 7
  9. 2016Multiple Instance Learning Convolutional Neural Networks for Object Recognitioncited by 6
  10. 2021Multi-Attention Multiple Instance Learningcited by 6

Built on by

Not cited yet.