← Back to all news
arXiv Machine Learning

A Feature Selection Layer Approach for Multi-Class Classification on Neural Networks

The paper introduces extensions to the Feature Selection Layer, an embedded feature weighting mechanism for neural networks, to improve interpretability in multi‑class classification. Experiments show that the best extension matches existing methods in identifying globally relevant features while outperforming them in capturing label‑specific relevance. The approach leverages the neural network’s internal dynamics, eliminating the need for post‑processing to reveal how individual features influence specific label predictions.

Related stories

arXiv Machine Learning
Oct 23

Post-Hoc Feature Selection Layer for Neural Networks Interpretability

The paper introduces a post‑hoc Feature Selection Layer (FSL) that can be added to frozen pre‑trained neural networks on tabular data to highlight the most important features. This lightweight, trainable module fine‑tunes feature weights based on the original model’s outputs without altering its architecture or parameters. Experiments on synthetic and real‑world datasets show that the post‑hoc FSL preserves predictive performance while improving interpretability, outperforming other post‑hoc methods such as Integrated Gradients and SHAP.

By Jo\~ao Kenji Suwa, Jo\~ao Pedro Silveira e Silva, Bruno Iochins Grisci
fine-tuningbenchmarkssafety
More like this →
arXiv Machine Learning
Aug 31

Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attribution

The paper introduces SEMGNN, an end‑to‑end self‑explainable multi‑label graph neural network that simultaneously classifies nodes and identifies edges contributing to each predicted label. Unlike post‑hoc explainers, SEMGNN jointly learns a predictor and a sparse edge‑mask explainer, leveraging label‑label correlations to improve classification and generate distinct, coherent explanations for each label. Experiments on synthetic and real‑world networks in social, entertainment, and life‑science domains demonstrate competitive predictive performance and more faithful, compact label‑conditioned explanations.

By Yingqi Feng, Yufei Tang, Min Shi, Xingquan Zhu
More like this →
arXiv Machine Learning
Sep 10

Interpretable Network-assisted Random Forest+

The paper introduces Interpretable Network-assisted Random Forest+ (RF+), a family of flexible models that combine the predictive power of random forests with network information. It offers intrinsic interpretability by providing global and local feature importance measures, as well as sample influence metrics, allowing researchers to assess both feature effects and the contribution of network neighbors. The authors claim that RF+ achieves competitive prediction accuracy while remaining transparent, making it suitable for high-impact problems where understanding model decisions is crucial.

By Tiffany M. Tang, Elizaveta Levina, Ji Zhu
safety
More like this →