# Feature Importance Ranking for Deep Learning

arXiv: https://arxiv.org/abs/2010.08973 · HTML: https://mlsanity.com/paper/2010.08973/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2020.

## Built on by (most cited first, 30 of 31)

- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation](https://mlsanity.com/paper/2206.06487/) (2022)
- [Accelerating Shapley Explanation via Contributive Cooperator Selection](https://mlsanity.com/paper/2206.08529/) (2022)
- [Knowledge-augmented Deep Learning and Its Applications: A Survey](https://mlsanity.com/paper/2212.00017/) (2022)
- [Sequential Attention for Feature Selection](https://mlsanity.com/paper/2209.14881/) (2022)
- [Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks](https://mlsanity.com/paper/2303.07200/) (2023)
- [Graph Convolutional Network-based Feature Selection for High-dimensional and Low-sample Size Data](https://mlsanity.com/paper/2211.14144/) (2022)
- [Enhancing Interpretability and Generalizability in Extended Isolation Forests](https://mlsanity.com/paper/2310.05468/) (2023)
- [TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Ordering](https://mlsanity.com/paper/2410.13203/) (2024)
- [Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction](https://mlsanity.com/paper/2402.04154/) (2024)
- [RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank](https://mlsanity.com/paper/2405.01848/) (2024)
- [Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities](https://mlsanity.com/paper/2202.05610/) (2022)
- [Unveiling the Power of Sparse Neural Networks for Feature Selection](https://mlsanity.com/paper/2408.04583/) (2024)
- [Towards Understanding the Effectiveness of Attention Mechanism](https://mlsanity.com/paper/2106.15067/) (2021)
- [Variance Tolerance Factors For Interpreting ALL Neural Networks](https://mlsanity.com/paper/2209.13858/) (2022)
- [Effective Neural Network L0 Regularization With BinMask](https://mlsanity.com/paper/2304.11237/) (2023)
- [Learning Active Subspaces and Discovering Important Features with Gaussian Radial Basis Functions Neural Networks](https://mlsanity.com/paper/2307.05639/) (2023)
- [Factor Importance Ranking and Selection using Total Indices](https://mlsanity.com/paper/2401.00800/) (2024)
- [On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations](https://mlsanity.com/paper/2508.10490/) (2025)
- [An Embedded Feature Selection Framework for Control](https://mlsanity.com/paper/2206.11064/) (2022)
- [T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients](https://mlsanity.com/paper/2404.16495/) (2024)
- [Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2409.02438/) (2024)
- [Top-k Regularization for Supervised Feature Selection](https://mlsanity.com/paper/2106.02197/) (2021)
- [Ranking Feature-Block Importance in Artificial Multiblock Neural Networks](https://mlsanity.com/paper/2109.10279/) (2021)
- ["Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation](https://mlsanity.com/paper/2205.05980/) (2022)
- [A-SFS: Semi-supervised Feature Selection based on Multi-task Self-supervision](https://mlsanity.com/paper/2207.09061/) (2022)
- [Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection](https://mlsanity.com/paper/2210.06891/) (2022)
- [Knowledge Discovery from Atomic Structures using Feature Importances](https://mlsanity.com/paper/2303.09453/) (2023)
- [EasyFS: an Efficient Model-free Feature Selection Framework via Elastic Transformation of Features](https://mlsanity.com/paper/2402.05954/) (2024)
- [rECGnition_v1.0: Arrhythmia detection using cardiologist-inspired multi-modal architecture incorporating demographic attributes in ECG](https://mlsanity.com/paper/2410.18985/) (2024)

## Abstract (arXiv)

Feature importance ranking has become a powerful tool for explainable AI. However, its nature of combinatorial optimization poses a great challenge for deep learning. In this paper, we propose a novel dual-net architecture consisting of operator and selector for discovery of an optimal feature subset of a fixed size and ranking the importance of those features in the optimal subset simultaneously. During learning, the operator is trained for a supervised learning task via optimal feature subset candidates generated by the selector that learns predicting the learning performance of the operator working on different optimal subset candidates. We develop an alternate learning algorithm that trains two nets jointly and incorporates a stochastic local search procedure into learning to address the combinatorial optimization challenge. In deployment, the selector generates an optimal feature subset and ranks feature importance, while the operator makes predictions based on the optimal subset for test data. A thorough evaluation on synthetic, benchmark and real data sets suggests that our approach outperforms several state-of-the-art feature importance ranking and supervised feature selection methods. (Our source code is available: https://github.com/maksym33/FeatureImportanceDL)