paper-with-me

Papers

Multi-Layer Attention-Based Explainability via Transformers for Tabular Data

2023-02-28 · Andrea Treviño Gavito, Diego Klabjan, Jean Utke

We propose a graph-oriented attention-based explainability method for tabular data. Tasks involving tabular data have been solved mostly using traditional tree-based machine learning models which have the challenges of feature selection and engineering. With that in mind, we consider a transformer architecture for tabular data, which is amenable to explainability, and present a novel way to leverage self-attention mechanism to provide explanations by taking into account the attention matrices of all heads and layers as a whole. The matrices are mapped to a graph structure where groups of features correspond to nodes and attention values to arcs. By finding the maximum probability paths in the graph, we identify groups of features providing larger contributions to explain the model's predictions. To assess the quality of multi-layer attention-based explanations, we compare them with popular attention-, gradient-, and perturbation-based explanability methods.

📄 PDF Abstract BibTeX arXiv:2302.14278

Code (0)

등록된 구현이 없습니다.

Tasks

feature selection

Methods 이 논문이 사용한 방법론

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

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

Polynomial-based Self-Attention for Table Representation learning

2023-12-12 · Jayoung Kim, Yehjin Shin, Jeongwhan Choi, Hyowon Wi 외

Structured data, which constitutes a significant portion of existing data types, has been a long-standing research topic in the field of machine learning. Various representation learning methods for tabular data have bee…

DecoderRepresentation Learning

Tabular data generation with tensor contraction layers and transformers

2024-12-06 · Aníbal Silva, André Restivo, Moisés Santos, Carlos Soares

Generative modeling for tabular data has recently gained significant attention in the Deep Learning domain. Its objective is to estimate the underlying distribution of the data. However, estimating the underlying distrib…

Density EstimationTabular Data Generation

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity

2024-04-04 · Walid Bousselham, Angie Boggust, Sofian Chaybouti, Hendrik Strobelt 외

Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models rem…

Sensitivity

Importance Scoring of Transformer Attention Heads in Learning Tabular Data

2026-08-27 · Ahmad Jad Allah, Kazi F. Akhter, Md. Kamrozzaman Bhuiyan, Manar D. Samad arxiv

Computationally demanding and opaque deep learning models can be better understood and optimized by analyzing how they transform data. While deep transformers have been widely studied in computer vision and natural langu…