Gaussian Process Neural Additive Models

被引:0
|
作者
Zhang, Wei [1 ]
Barr, Brian [2 ]
Paisley, John [1 ]
机构
[1] Columbia Univ, New York, NY 10025 USA
[2] Capital One, New York, NY USA
来源
THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 15 | 2024年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep neural networks have revolutionized many fields, but their black-box nature also occasionally prevents their wider adoption in fields such as healthcare and finance, where interpretable and explainable models are required. The recent development of Neural Additive Models (NAMs) is a significant step in the direction of interpretable deep learning for tabular datasets. In this paper, we propose a new subclass of NAMs that use a single-layer neural network construction of the Gaussian process via random Fourier features, which we call Gaussian Process Neural Additive Models (GP-NAM). GP-NAMs have the advantage of a convex objective function and number of trainable parameters that grows linearly with feature dimensionality. It suffers no loss in performance compared to deeper NAM approaches because GPs are well-suited for learning complex non-parametric univariate functions. We demonstrate the performance of GP-NAM on several tabular datasets, showing that it achieves comparable or better performance in both classification and regression tasks with a large reduction in the number of parameters.
引用
收藏
页码:16865 / 16872
页数:8
相关论文
共 50 条
  • [41] Identification of Gaussian Process State Space Models
    Eleftheriadis, Stefanos
    Nicholson, Thomas F. W.
    Deisenroth, Marc P.
    Hensman, James
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [42] Gaussian Process Dynamical Models for Emotion Recognition
    Garcia, Hernan F.
    Alvarez, Mauricio A.
    Orozco, Alvaro
    ADVANCES IN VISUAL COMPUTING (ISVC 2014), PT II, 2014, 8888 : 799 - 808
  • [43] Stability of Controllers for Gaussian Process Forward Models
    Vinogradska, Julia
    Bischoff, Bastian
    Nguyen-Tuong, Duy
    Schmidt, Henner
    Romer, Anne
    Peters, Jan
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 48, 2016, 48
  • [44] Gaussian process dynamical models for human motion
    Wang, Jack M.
    Fleet, David J.
    Hertzmann, Aaron
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2008, 30 (02) : 283 - 298
  • [45] Gaussian process latent class choice models
    Sfeir, Georges
    Rodrigues, Filipe
    Abou-Zeid, Maya
    TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2022, 136
  • [46] Optimization of Gaussian Process Models with Evolutionary Algorithms
    Petelin, Dejan
    Filipic, Bogdan
    Kocijan, Jus
    ADAPTIVE AND NATURAL COMPUTING ALGORITHMS, PT I, 2011, 6593 : 420 - 429
  • [47] Generic inference in latent Gaussian process models
    Bonilla, Edwin V.
    Krauth, Karl
    Dezfouli, Amir
    Journal of Machine Learning Research, 2019, 20
  • [48] Generic Inference in Latent Gaussian Process Models
    Bonilla, Edwin V.
    Krauth, Karl
    Dezfouli, Amir
    JOURNAL OF MACHINE LEARNING RESEARCH, 2019, 20
  • [49] Hierarchical Gaussian Process Models for Improved Metamodeling
    Knudde, Nicolas
    Dutordoir, Vincent
    Van der Herten, Joachim
    Couckuyt, Ivo
    Dhaene, Tom
    ACM TRANSACTIONS ON MODELING AND COMPUTER SIMULATION, 2020, 30 (04):
  • [50] MOTION PREDICTION WITH GAUSSIAN PROCESS DYNAMICAL MODELS
    Qu, Shi
    Wu, Lingda
    Wei, Yingmei
    Yu, Ronghuan
    3RD INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND COMPUTER SCIENCE (ITCS 2011), PROCEEDINGS, 2011, : 162 - 165