paper-with-me

홈 › Papers

Trap of Feature Diversity in the Learning of MLPs

2021-12-02 · Dongrui Liu, Shaobo Wang, Jie Ren, Kangrui Wang, Sheng Yin, Huiqi Deng, Quanshi Zhang

In this paper, we focus on a typical two-phase phenomenon in the learning of multi-layer perceptrons (MLPs), and we aim to explain the reason for the decrease of feature diversity in the first phase. Specifically, people find that, in the training of MLPs, the training loss does not decrease significantly until the second phase. To this end, we further explore the reason why the diversity of features over different samples keeps decreasing in the first phase, which hurts the optimization of MLPs. We explain such a phenomenon in terms of the learning dynamics of MLPs. Furthermore, we theoretically explain why four typical operations can alleviate the decrease of the feature diversity.

📄 PDF Abstract BibTeX arXiv:2112.00980

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

2020-09-24 · ICLR 2021 1 · Keyulu Xu, Mozhi Zhang, Jingling Li, Simon S. Du 외

We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical results when extrapolating with neural n…

A ZeNN architecture to avoid the Gaussian trap

2025-05-26 · Luís Carvalho, João L. Costa, José Mourão, Gonçalo Oliveira

We propose a new simple architecture, Zeta Neural Networks (ZeNNs), in order to overcome several shortcomings of standard multi-layer perceptrons (MLPs). Namely, in the large width limit, MLPs are non-parametric, they do…

Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values

2025-12-11 · Brian P. Powell, Jordan A. Caraballo-Vega, Mark L. Carroll, Thomas Maxwell 외 arxiv

We report the discovery that binary encoding allows neural networks to extrapolate periodic functions beyond their training bounds. We introduce Normalized Base-2 Encoding (NB2E) as a method for encoding continuous numer…

Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs

2022-12-18 · Chenxiao Yang, Qitian Wu, Jiahua Wang, Junchi Yan

Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional message passing layers to allow features to f…

Representation Learning

Facilitating bootstrapped and rarefaction-based microbiome diversity analysis with q2-boots

2024-08-10 · Isaiah Raspet, Elizabeth Gehret, Chloe Herman, Jeff Meilander 외

Background: We present q2-boots, a QIIME 2 plugin that facilitates bootstrapped and rarefaction-based microbiome diversity analysis. This plugin provides eight new actions that allow users to apply any of thirty differen…

Diversity