paper-with-me

Papers

GANDALF: Gated Adaptive Network for Deep Automated Learning of Features

2022-07-18 · Manu Joseph, Harsh Raj

We propose a novel high-performance, interpretable, and parameter \& computationally efficient deep learning architecture for tabular data, Gated Adaptive Network for Deep Automated Learning of Features (GANDALF). GANDALF relies on a new tabular processing unit with a gating mechanism and in-built feature selection called Gated Feature Learning Unit (GFLU) as a feature representation learning unit. We demonstrate that GANDALF outperforms or stays at-par with SOTA approaches like XGBoost, SAINT, FT-Transformers, etc. by experiments on multiple established public benchmarks. We have made available the code at github.com/manujosephv/pytorch_tabular under MIT License.

📄 PDF Abstract BibTeX arXiv:2207.08548

Code (2)

manujosephv/GATE 공식 구현 pytorch
manujosephv/pytorch_tabular pytorch

Tasks

feature selectionregressionRepresentation Learningtabular-classification

Methods 이 논문이 사용한 방법론

GANDALF We propose a novel high-performance, interpretable, and parameter \& computationally efficient deep learning architecture for tabular data, Gated Adaptive Network for Deep…
Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Gandalf the Red: Adaptive Security for LLMs

2025-01-14 · Niklas Pfister, Václav Volhejn, Manuel Knott, Santiago Arias 외

Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior and the usability penalties imposed on leg…

BlockingLanguage ModelingLanguage ModellingLarge Language Model+1

Learning label-label correlations in Extreme Multi-label Classification via Label Features

2024-05-03 · Siddhant Kharbanda, Devaansh Gupta, Erik Schultheis, Atmadeep Banerjee 외

Extreme Multi-label Text Classification (XMC) involves learning a classifier that can assign an input with a subset of most relevant labels from millions of label choices. Recent works in this domain have increasingly fo…

Extreme Multi-Label ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti Label Text Classification+4

Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models

2025-07-09 · Aaron Dharna, Cong Lu, Jeff Clune arxiv

Multi-agent interactions have long fueled innovation, from natural predator-prey dynamics to the space race. Self-play (SP) algorithms try to harness these dynamics by pitting agents against ever-improving opponents, the…

Reinforcement Learning

Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software

2025-04-22 · Anjali Khurana, Xiaotian Su, April Yi Wang, Parmit K Chilana

Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective use…

Language ModelingLanguage ModellingLarge Language Model

How Usable is Automated Feature Engineering for Tabular Data?

2025-08-19 · Bastian Schäfer, Lennart Purucker, Maciej Janowski, Frank Hutter arxiv

Tabular data, consisting of rows and columns, is omnipresent across various machine learning applications. Each column represents a feature, and features can be combined or transformed to create new, more informative fea…

Feature Engineering