Redirigiendo al acceso original de articulo en 19 segundos...
Inicio  /  Algorithms  /  Vol: 16 Par: 8 (2023)  /  Artículo
ARTÍCULO
TITULO

Multiple Instance Learning with Trainable Soft Decision Tree Ensembles

Andrei Konstantinov    
Lev Utkin and Vladimir Muliukha    

Resumen

A new random forest-based model for solving the Multiple Instance Learning problem under small tabular data, called the Soft Tree Ensemble Multiple Instance Learning, 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 Soft Tree Ensemble Multiple Instance Learning model, including soft decision trees, neural networks, the attention mechanism and a classifier, is trained in an end-to-end manner. Numerical experiments with well-known real tabular datasets show that the proposed model can outperform many existing multiple instance learning models. A code implementing the model is publicly available.

 Artículos similares

       
 
Panagiotis Filippakis, Stefanos Ougiaroglou and Georgios Evangelidis    
Reducing the size of the training set, which involves replacing it with a condensed set, is a widely adopted practice to enhance the efficiency of instance-based classifiers while trying to maintain high classification accuracy. This objective can be ach... ver más
Revista: Information

 
Jesús Dassaef López-Barrios, Jesús Arturo Escobedo Cabello, Alfonso Gómez-Espinosa and Luis-Enrique Montoya-Cavero    
In this paper, a mask region-based convolutional neural network (Mask R-CNN) is used to improve the performance of machine vision in the challenging task of detecting peduncles and fruits of green sweet peppers (Capsicum annuum L.) in greenhouses. One of... ver más
Revista: Applied Sciences

 
Arturo Benjamín Hurtado-Pérez, Abraham de Jesús Pablo-Sotelo, Fabián Ramírez-López, Jorge Javier Hernández-Gómez and Miguel Felix Mata-Rivera    
Launching satellites into the Earth?s orbit is a critical area of research, and very demanding satellite services increase exponentially as modern society takes shape. At the same time, the costs of developing and launching satellite missions with shorte... ver más
Revista: Aerospace

 
Lujie Xiong, Yanping Jiao, Fengwei Wang and Shijian Zhou    
This study utilizes 27 years of sea level anomaly (SLA) data obtained from satellite altimetry to investigate spatial?temporal variations in the South China Sea (SCS). The local mean decomposition (LMD) method is applied to decompose the sea level data i... ver más

 
Eunwoo Kim    
Multi-task learning (MTL) is a learning strategy for solving multiple tasks simultaneously while exploiting commonalities and differences between tasks for improved learning efficiency and prediction performance. Despite its potential, there remain sever... ver más
Revista: Applied Sciences