Abstract
In many fields, the interpretability of machine learning models holds equal importance to their prediction accuracy. Highly accurate predictions are possible with a multilayer perceptron (MLP) neural network, but its application in high-risk fields is constrained by its lack of interpretability. To solve this issue, this paper introduces an MLP with a presingle-connection layer (SMLP). The SMLP incorporates a single-to-single connection layer with the ReLU function before the original MLP. By examining the weights of the single-connection layer after training the model, the significance of the input features can be determined. The experimental results demonstrate that this method can accurately measure the feature importance with the MLP. It offers advantages such as a straightforward theory, practical implementation, strong stability, and high reliability when compared with other widely used feature importance algorithms. Moreover, this measure effectively reveals the black box of the MLP, indicates the influence of input features on the prediction, and provides a quantitative standard for feature selection in MLP.
Similar content being viewed by others
References
Li J, Hassani A, Walton S, Shi H (2021) Convmlp: hierarchical convolutional mlps for vision. arXiv e-prints. https://doi.org/10.48550/ARXIV.2109.04454
He K, Gkioxari G, Dollár P, Girshick R (2020) Mask r-cnn. IEEE Trans Pattern Anal Mach Intell 42(2):386–397. https://doi.org/10.1109/TPAMI.2018.2844175
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, USA, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Xiao T, Liu Y, Zhou B, Jiang Y, Sun J (2018) Unified perceptual parsing for scene understanding. In: Proceedings of the European conference on computer vision (ECCV). https://doi.org/10.48550/arXiv.1807.10221
Tolstikhin IO, Houlsby N, Kolesnikov A, Beyer L, Zhai X, Unterthiner T, Yung J, Steiner A, Keysers D, Uszkoreit J, Lucic M, Dosovitskiy A (2021) Mlp-mixer: an all-mlp architecture for vision. In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Vaughan JW (eds) Advances in neural information processing systems, vol 34, pp 24261–24272. https://doi.org/10.48550/arXiv.2105.01601
Desai M, Shah M (2021) An anatomization on breast cancer detection and diagnosis employing multi-layer perceptron neural network (mlp) and convolutional neural network (cnn). Clin eHealth 4:1–11. https://doi.org/10.1016/j.ceh.2020.11.002
Meghanadh D, Kumar Maurya V, Tiwari A, Dwivedi R (2022) A multi-criteria landslide susceptibility mapping using deep multi-layer perceptron network: a case study of Srinagar-Rudraprayag Region (India). Adv Space Res 69(4):1883–1893. https://doi.org/10.1016/j.asr.2021.10.021
Sharma R, Kim M, Gupta A (2022) Motor imagery classification in brain-machine interface with machine learning algorithms: classical approach to multi-layer perceptron model. Biomed Signal Process Control 71:103101. https://doi.org/10.1016/j.bspc.2021.103101
Shen Z, Bi Y, Wang Y, Guo C (2020) Mlp neural network-based recursive sliding mode dynamic surface control for trajectory tracking of fully actuated surface vessel subject to unknown dynamics and input saturation. Neurocomputing 377:103–112. https://doi.org/10.1016/j.neucom.2019.08.090
Casalicchio G, Molnar C, Bischl B (2019) Visualizing the feature importance for black box models. In: Berlingerio M, Bonchi F, Gärtner T, Hurley N, Ifrim G (eds) Machine learning and knowledge discovery in databases, pp 655–670. https://doi.org/10.1007/978-3-030-10925-7_40
Luíza da Costa N, Dias de Lima M, Barbosa R (2021) Evaluation of feature selection methods based on artificial neural network weights. Expert Syst Appl 168:114312. https://doi.org/10.1016/j.eswa.2020.114312
Doshi-Velez F, Kim B (2017) Towards a rigorous science of interpretable machine learning. arXiv e-prints. https://doi.org/10.48550/ARXIV.1702.08608
Mihaljević B, Bielza C, Larrañaga P (2021) Bayesian networks for interpretable machine learning and optimization. Neurocomputing 456:648–665. https://doi.org/10.1016/j.neucom.2021.01.138
Miller T (2019) Explanation in artificial intelligence: Insights from the social sciences. Artif Intell 267:1–38. https://doi.org/10.1016/j.artint.2018.07.007
Stiglic G, Kocbek P, Fijacko N, Zitnik M, Verbert K, Cilar L (2020) Interpretability of machine learning-based prediction models in healthcare. WIREs Data Min Knowl Discov 10(5):1379. https://doi.org/10.1002/widm.1379
Khemphila A, Boonjing V (2011) Heart disease classification using neural network and feature selection. In: 2011 21st international conference on systems engineering. IEEE Computer Society, Los Alamitos, CA, USA, pp 406–409. https://doi.org/10.1109/ICSEng.2011.80
Shang R, Kong J, Wang L, Zhang W, Wang C, Li Y, Jiao L (2023) Unsupervised feature selection via discrete spectral clustering and feature weights. Neurocomputing 517:106–117. https://doi.org/10.1016/j.neucom.2022.10.053
Jerome HF (1991) Multivariate adaptive regression splines. Ann Stat 19(1):1–67. https://doi.org/10.1214/aos/1176347963
Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Gevrey M, Dimopoulos I, Lek S (2003) Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Model 160(3):249–264. https://doi.org/10.1016/S0304-3800(02)00257-0
Ribeiro MT, Singh S, Guestrin C (2016) “why should i trust you?”: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. KDD’16. Association for Computing Machinery, New York, NY, USA, pp 1135–1144. https://doi.org/10.1145/2939672.2939778
Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Guyon I, Luxburg UV, Bengio S, Wallach, H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30, pp 4768–4777. https://doi.org/10.48550/arXiv.1705.07874
Fisher A, Rudin C, Dominici F (2019) All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. J Mach Learn Res 20:177. https://doi.org/10.48550/arXiv.1801.01489
Hastie T, Tibshirani R, Friedman JH, Friedman JH (2009) The elements of statistical learning: data mining, inference, and prediction, vol 2. Springer, New York. https://doi.org/10.1007/978-0-387-84858-7
Molnar C (2020) Interpretable machine learning. Lulu.com, Morrisville
Ventura F, Greco S, Apiletti D, Cerquitelli T (2022) Trusting deep learning natural-language models via local and global explanations. Knowl Inf Syst 64(7):1863–1907. https://doi.org/10.1007/s10115-022-01690-9
Han K, Wang Y, Zhang C, Li C, Xu C (2018) Autoencoder inspired unsupervised feature selection. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2941–2945. https://doi.org/10.1109/ICASSP.2018.8462261
Wu X, Cheng Q (2020) Fractal autoencoders for feature selection. arXiv e-prints. https://doi.org/10.48550/arXiv.2010.09430
Wang S, Ding Z, Fu Y (2017) Feature selection guided auto-encoder. In: Proceedings of the thirty-first AAAI conference on artificial intelligence, pp 2725–2731. https://doi.org/10.5555/3298483.3298631
Wang X, Wang Z, Zhang Y, Jiang X, Cai Z (2022) Latent representation learning based autoencoder for unsupervised feature selection in hyperspectral imagery. Multimed Tools Appl 81:1–15. https://doi.org/10.1007/s11042-020-10474-8
Garson GD (1991) Interpreting neural-network connection weights. AI Expert 6(4):46–51
Olden JD, Joy MK, Death RG (2004) An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol Model 178(3):389–397. https://doi.org/10.1016/j.ecolmodel.2004.03.013
Fischer A (2015) How to determine the unique contributions of input-variables to the nonlinear regression function of a multilayer perceptron. Ecol Model 309–310:60–63. https://doi.org/10.1016/j.ecolmodel.2015.04.015
Kemp SJ, Zaradic P, Hansen F (2007) An approach for determining relative input parameter importance and significance in artificial neural networks. Ecol Model 204(3):326–334. https://doi.org/10.1016/j.ecolmodel.2007.01.009
Pires dos Santos R, Dean DL, Weaver JM, Hovanski Y (2019) Identifying the relative importance of predictive variables in artificial neural networks based on data produced through a discrete event simulation of a manufacturing environment. Int J Model Simul 39(4):234–245. https://doi.org/10.1080/02286203.2018.1558736
Cui P, Athey S (2022) Stable learning establishes some common ground between causal inference and machine learning. Nat Mach Intell 4:110–115. https://doi.org/10.1038/s42256-022-00445-z
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Hartman EJ, Keeler JD, Kowalski JM (1990) Layered neural networks with gaussian hidden units as universal approximations. Neural Comput 2(2):210–215. https://doi.org/10.1162/neco.1990.2.2.210
Lek S, Park YS (2008) Multilayer perceptron. Academic Press, Oxford, pp 2455–2462. https://doi.org/10.1016/B978-008045405-4.00162-2
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. MIT Press, Cambridge, pp 318–362
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366. https://doi.org/10.1016/0893-6080(89)90020-8
Zhang Z, Beck MW, Winkler DA, Huang B, Sibanda W, Goyal H (2018) Opening the black box of neural networks: methods for interpreting neural network models in clinical applications. Ann Transl Med 6(11):216. https://doi.org/10.21037/atm.2018.05.32
Benitez JM, Castro JL, Requena I (1997) Are artificial neural networks black boxes? IEEE Trans Neural Netw 8(5):1156–1164. https://doi.org/10.1109/72.623216
Castelvecchi D (2016) Can we open the black box of AI? Nat News 538(7623):20–23. https://doi.org/10.1038/538020a
Dayhoff JE, DeLeo JM (2001) Artificial neural networks. Cancer 91(S8):1615–1635. https://doi.org/10.1002/1097-0142(20010415)91:8+<1615::AID-CNCR1175>3.0.CO;2-L
Roberts JD, Caserio MC (1977) Basic principles of organic chemistry. WA Benjamin, Menlo Park
Kokaly RF, Clark RN, Swayze GA, Livo KE, Hoefen TM, Pearson NC, Wise RA, Benzel WM, Lowers HA, Driscoll RL, Klein AJ (2017) Usgs spectral library version 7. Report. https://doi.org/10.3133/ds1035
Fisher RA (1921) On the ‘probable error’ of a coefficient of correlation deduced from a small sample. Metron 1:1–32
Sawyer SF (2009) Analysis of variance: the fundamental concepts. J Manual Manipulat Ther 17(2):27–38. https://doi.org/10.1179/jmt.2009.17.2.27E
Lin H, Ding H (2011) Predicting ion channels and their types by the dipeptide mode of pseudo amino acid composition. J Theor Biol 269(1):64–69. https://doi.org/10.1016/j.jtbi.2010.10.019
Han J, Pei J, Kamber M (2011) Data mining: concepts and techniques. Elsevier Science, Amsterdam
Al Shalabi L, Shaaban Z, Kasasbeh B (2006) Data mining: a preprocessing engine. J Comput Sci 2(9):735–739. https://doi.org/10.3844/jcssp.2006.735.739
Patro SGK, Sahu KK (2015) Normalization: a preprocessing stage. arXiv e-prints. https://doi.org/10.48550/ARXIV.1503.06462
Hong Y, Bonhomme C, Soheilian B, Chebbo G (2017) Effects of using different sources of remote sensing and geographic information system data on urban stormwater 2d–1d modeling. Appl Sci. https://doi.org/10.3390/app7090904
Strobl C, Boulesteix A-L, Zeileis A, Hothorn T (2007) Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinform 8:25. https://doi.org/10.1186/1471-2105-8-25
Altmann A, Toloşi L, Sander O, Lengauer T (2010) Permutation importance: a corrected feature importance measure. Bioinformatics 26(10):1340–1347. https://doi.org/10.1093/bioinformatics/btq134
Acknowledgements
This research was supported by the NATIONAL NATURAL SCIENCE FOUNDATION OF CHINA [Grant Nos. 41872214 and 42072232].
Author information
Authors and Affiliations
Contributions
WZ, LZ and XS wrote the main manuscript text. WZ and ZY helped to write code and conduct experiments. WZ, LZ, XS, HZ, JS and XZ helped to revise the paper. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, W., Shen, X., Zhang, H. et al. Feature importance measure of a multilayer perceptron based on the presingle-connection layer. Knowl Inf Syst 66, 511–533 (2024). https://doi.org/10.1007/s10115-023-01959-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-023-01959-7