paper-with-me

Papers

Learning a Decision Tree Algorithm with Transformers

2024-02-06 · Yufan Zhuang, Liyuan Liu, Chandan Singh, Jingbo Shang, Jianfeng Gao

Decision trees are renowned for their ability to achieve high predictive performance while remaining interpretable, especially on tabular data. Traditionally, they are constructed through recursive algorithms, where they partition the data at every node in a tree. However, identifying a good partition is challenging, as decision trees optimized for local segments may not yield global generalization. To address this, we introduce MetaTree, a transformer-based model trained via meta-learning to directly produce strong decision trees. Specifically, we fit both greedy decision trees and globally optimized decision trees on a large number of datasets, and train MetaTree to produce only the trees that achieve strong generalization performance. This training enables MetaTree to emulate these algorithms and intelligently adapt its strategy according to the context, thereby achieving superior generalization performance.

📄 PDF Abstract BibTeX arXiv:2402.03774

Code (1)

evanzhuang/metatree 공식 구현 pytorch

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Generalizing Tree Models for Improving Prediction Accuracy

2021-01-01 · Jaemin Yoo, Lee Sael

Can we generalize and improve the representation power of tree models? Tree models are often favored over deep neural networks due to their interpretable structures in problems where the interpretability is required, suc…

Prediction

Medication Mention Detection in Tweets Using ELECTRA Transformers and Decision Trees

2020-12-01 · SMM4H (COLING) 2020 12 · Lung-Hao Lee, Po-Han Chen, Hao-Chuan Kao, Ting-Chun Hung 외

This study describes our proposed model design for the SMM4H 2020 Task 1. We fine-tune ELECTRA transformers using our trained SVM filter for data augmentation, along with decision trees to detect medication mentions in t…

Data Augmentation

Challenging Gradient Boosted Decision Trees with Tabular Transformers for Fraud Detection at Booking.com

2024-05-22 · Sergei Krutikov, Bulat Khaertdinov, Rodion Kiriukhin, Shubham Agrawal 외

Transformer-based neural networks, empowered by Self-Supervised Learning (SSL), have demonstrated unprecedented performance across various domains. However, related literature suggests that tabular Transformers may strug…

Fraud DetectionSelection biasSelf-Supervised Learning

Transformers Boost the Performance of Decision Trees on Tabular Data across Sample Sizes

2025-02-04 · Mayuka Jayawardhana, Renbo, Samuel Dooley, Valeriia Cherepanova 외

Large language models (LLMs) perform remarkably well on tabular datasets in zero- and few-shot settings, since they can extract meaning from natural language column headers that describe features and labels. Similarly, T…

In-Context LearningNatural Language Understanding

SALT : Sharing Attention between Linear layer and Transformer for tabular dataset

2021-09-29 · Juseong Kim, Jinsun Park, Giltae Song

Handling tabular data with deep learning models is a challenging problem despite their remarkable success in vision and language processing applications. Therefore, many practitioners still rely on classical models such …

Deep Learning