mlsanityData to 14 Oct 2026

CatNet: Controlling the False Discovery Rate in LSTM with SHAP Feature Importance and Gaussian Mirrors

arXiv 2411.16666 ↗First posted 25 Nov 2024stat.ML cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce CatNet, an algorithm that effectively controls False Discovery Rate (FDR) and selects significant features in LSTM. CatNet employs the derivative of SHAP values to quantify the feature importance, and constructs a vector-formed mirror statistic for FDR control with the Gaussian Mirror algorithm. To avoid instability due to nonlinear or temporal correlations among features, we also propose a new kernel-based independence measure. CatNet performs robustly on different model settings with both simulated and real-world data, which reduces overfitting and improves interpretability of the model. Our framework that introduces SHAP for feature importance in FDR control algorithms and improves Gaussian Mirror can be naturally extended to other time-series or sequential deep learning models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 44 references that are in the map. First posted on arXiv 25 Nov 2024.

Builds on

21 of 44 references.

References · 21

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2017Interpretation of Neural Networks is Fragilecited by 444
  3. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 420
  4. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 364
  5. 2016Panning for Gold: Model-X Knockoffs for High-dimensional Controlled Variable Selectioncited by 121
  6. 2014Controlling the false discovery rate via knockoffscited by 97
  7. 2018DeepPINK: reproducible feature selection in deep neural networkscited by 41
  8. 2015De-biasing the Lasso: Optimal Sample Size for Gaussian Designscited by 35
  9. 2016A knockoff filter for high-dimensional selective inferencecited by 25
  10. 2016Interpretation of Prediction Models Using the Input Gradientcited by 24
  11. 2020False Discovery Rate Control via Data Splittingcited by 12
  12. 2019Metropolized Knockoff Samplingcited by 10
9 more
  1. 2019Controlling False Discovery Rate Using Gaussian Mirrorscited by 10
  2. 2020A Scale-free Approach for False Discovery Rate Control in Generalized Linear Modelscited by 8
  3. 2024FDR-Controlled Portfolio Optimization for Sparse Financial Index Trackingcited by 5
  4. 2020Neural Gaussian Mirror for Controlled Feature Selection in Neural Networkscited by 3
  5. 2020Competition-based control of the false discovery proportioncited by 3
  6. 2022Near-optimal multiple testing in Bayesian linear models with finite-sample FDR controlcited by 3
  7. 2014Generalized Twin Gaussian Processes using Sharma-Mittal Divergencecited by 2
  8. 2022Landmark Tracking in Liver US images Using Cascade Convolutional Neural Networks with Long Short-Term Memorycited by 2
  9. 2024DeepLINK-T: deep learning inference for time series data using knockoffs and LSTMcited by 2

Built on by

Not cited yet.