English
Related papers

Related papers: XNNTab -- Interpretable Neural Networks for Tabula…

200 papers

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Deep neural networks (DNNs) have shown exceptional performances in a wide range of tasks and have become the go-to method for problems requiring high-level predictive power. There has been extensive research on how DNNs arrive at their…

Machine Learning · Computer Science 2023-02-21 Mattias Luber , Anton Thielmann , Benjamin Säfken

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

Deep learning models have become popular in the analysis of tabular data, as they address the limitations of decision trees and enable valuable applications like semi-supervised learning, online learning, and transfer learning. However,…

Machine Learning · Computer Science 2024-02-29 Jiaqi Luo , Shixin Xu

Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity…

Machine Learning · Computer Science 2026-02-11 Andres Saurez , Yousung Lee , Dongsoo Har

In this paper, we propose a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by learning a nonlinear embedding of a high-dimensional activation vector of a deep network layer into a…

Computer Vision and Pattern Recognition · Computer Science 2020-12-14 Zhongang Qi , Saeed Khorram , Fuxin Li

Sparse autoencoders (SAEs) are used to decompose neural network activations into sparsely activating features, but many SAE features are only interpretable at high activation strengths. To address this issue we propose to use binary sparse…

Machine Learning · Computer Science 2025-10-01 Lucia Quirke , Stepan Shabalin , Nora Belrose

While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results. We develop a new framework called Adaptive Explainable…

Machine Learning · Statistics 2020-06-03 Jie Chen , Joel Vaughan , Vijayan N. Nair , Agus Sudjianto

Tabular data are ubiquitous for the widespread applications of tables and hence have attracted the attention of researchers to extract underlying information. One of the critical problems in mining tabular data is how to understand their…

Machine Learning · Computer Science 2021-06-17 Lun Du , Fei Gao , Xu Chen , Ran Jia , Junshan Wang , Jiang Zhang , Shi Han , Dongmei Zhang

Tabular data poses unique challenges for deep learning due to its heterogeneous feature types, lack of spatial structure, and often limited sample sizes. We propose TabNSA, a novel deep learning framework that integrates Native Sparse…

Machine Learning · Computer Science 2026-02-11 Ali Eslamian , Qiang Cheng

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Machine Learning · Computer Science 2025-01-31 Charles O'Neill , Alim Gumran , David Klindt

Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are prone to overfitting and suffer from poor interpretability,…

Machine Learning · Computer Science 2021-07-13 Hejie Cui , Wei Dai , Yanqiao Zhu , Xiaoxiao Li , Lifang He , Carl Yang

Sparse autoencoders are a standard tool for uncovering interpretable latent representations in neural networks. Yet, their interpretation depends on the inputs, making their isolated study incomplete. Polynomials offer a solution; they…

Machine Learning · Computer Science 2025-10-21 Thomas Dooms , Ward Gauderis

Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we…

Machine Learning · Statistics 2016-11-23 Scott Wisdom , Thomas Powers , James Pitton , Les Atlas

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide guarantees on their expressiveness, present an approach based…

Machine Learning · Computer Science 2024-06-11 Benjamin Leblanc , Pascal Germain

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Machine Learning · Computer Science 2024-08-06 Charles O'Neill , Christine Ye , Kartheik Iyer , John F. Wu

Ongoing efforts to understand deep neural networks (DNN) have provided many insights, but DNNs remain incompletely understood. Improving DNN's interpretability has practical benefits, such as more accountable usage, better algorithm…

Machine Learning · Computer Science 2021-02-09 Erico Tjoa , Guan Cuntai

Deep neural networks have been proven powerful at processing perceptual data, such as images and audio. However for tabular data, tree-based models are more popular. A nice property of tree-based models is their natural interpretability. In…

Machine Learning · Computer Science 2018-06-20 Yongxin Yang , Irene Garcia Morillo , Timothy M. Hospedales

In high-dimensional and high-stakes contexts, ensuring both rigorous statistical guarantees and interpretability in feature extraction from complex tabular data remains a formidable challenge. Traditional methods such as Principal Component…

Machine Learning · Computer Science 2025-03-25 Xiaochen Zhang , Haoyi Xiong