mlsanityData to 7 Oct 2026

Full Bayesian Significance Testing for Neural Networks

arXiv 2401.13335 ↗First posted 24 Jan 2024stat.ML cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Significance testing aims to determine whether a proposition about the population distribution is the truth or not given observations. However, traditional significance testing often needs to derive the distribution of the testing statistic, failing to deal with complex nonlinear relationships. In this paper, we propose to conduct Full Bayesian Significance Testing for neural networks, called textitnFBST, to overcome the limitation in relationship characterization of traditional approaches. A Bayesian neural network is utilized to fit the nonlinear and multi-dimensional relationships with small errors and avoid hard theoretical derivation by computing the evidence value. Besides, textitnFBST can test not only global significance but also local and instance-wise significance, which previous testing methods don't focus on. Moreover, textitnFBST is a general framework that can be extended based on the measures selected, such as Grad-textitnFBST, LRP-textitnFBST, DeepLIFT-textitnFBST, LIME-textitnFBST. A range of experiments on both simulated and real data are conducted to show the advantages of our method.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 39 of its 90 references that are in the map. First posted on arXiv 24 Jan 2024.

Builds on

39 of 90 references.

References · 39

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  10. 2016Variational Inference: A Review for Statisticianscited by 1,466
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  12. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
27 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  2. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  3. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  4. 2015Weight Uncertainty in Neural Networkscited by 554
  5. 2017Convolutional Sequence to Sequence Learningcited by 550
  6. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  7. 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 330
  8. 2015Diffusion-Convolutional Neural Networkscited by 268
  9. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  10. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  11. 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 179
  12. 2023PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Predictioncited by 135
  13. 2017Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Predictioncited by 67
  14. 2018Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysiscited by 61
  15. 2022Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semanticscited by 58
  16. 2016Investigating the influence of noise and distractors on the interpretation of neural networkscited by 54
  17. 2020Coupled Layer-wise Graph Convolution for Transportation Demand Predictioncited by 54
  18. 2018A Simple and Effective Model-Based Variable Importance Measurecited by 50
  19. 2021Quantifying Uncertainty in Deep Spatiotemporal Forecastingcited by 48
  20. 2019AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networkscited by 39
  21. 2023Continuous Trajectory Generation Based on Two-Stage GANcited by 36
  22. 2022Uncertainty Quantification for Traffic Forecasting: A Unified Approachcited by 22
  23. 2019Empowering A* Search Algorithms with Neural Networks for Personalized Route Recommendationcited by 21
  24. 2019Significance Tests for Neural Networkscited by 17
  25. 2021STUaNet: Understanding uncertainty in spatiotemporal collective human mobilitycited by 11
  26. 2023Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defensecited by 6
  27. 2019SVM-based Deep Stacking Networkscited by 5

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 6.

8 papers.

  1. 2024BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysiscited by 16
  2. 2025Learning Universal Multi-level Market Irrationality Factors to Improve Stock Return Forecastingcited by 4
  3. 2024Learnable Sparse Customization in Heterogeneous Edge Computingcited by 2
  4. 2025Simple and Efficient Heterogeneous Temporal Graph Neural Networkcited by 2
  5. 2025ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Modelscited by 1
  6. 2025HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecastingcited by 1
  7. 2025ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputationcited by 0
  8. 2025RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Modelscited by 0