paper-with-me

Papers

Improving Graph Convolutional Networks with Non-Parametric Activation Functions

2018-02-26 · Simone Scardapane, Steven Van Vaerenbergh, Danilo Comminiello, Aurelio Uncini

Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs have been proposed, they only consider simple nonlinear activation functions in their layers, such as rectifiers or squashing functions. In this paper, we investigate the use of graph convolutional networks (GCNs) when combined with more complex activation functions, able to adapt from the training data. More specifically, we extend the recently proposed kernel activation function, a non-parametric model which can be implemented easily, can be regularized with standard $\ell_p$-norms techniques, and is smooth over its entire domain. Our experimental evaluation shows that the proposed architecture can significantly improve over its baseline, while similar improvements cannot be obtained by simply increasing the depth or size of the original GCN.

📄 PDF Abstract BibTeX arXiv:1802.09405

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Nonlinearity Enhanced Adaptive Activation Functions

2024-03-29 · David Yevick

A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational re…

Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks

2019-08-10 · Yang Liu, Jianpeng Zhang, Chao GAO, Jinghua Qu 외

Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions…

Parametric Rectified Power Sigmoid Units: Learning Nonlinear Neural Transfer Analytical Forms

2021-01-25 · Abdourrahmane Mahamane Atto, Sylvie Galichet, Dominique Pastor, Nicolas Méger

The paper proposes representation functionals in a dual paradigm where learning jointly concerns both linear convolutional weights and parametric forms of nonlinear activation functions. The nonlinear forms proposed for …

BIG-bench Machine Learning

Graph Convolutional Neural Networks as Parametric CoKleisli morphisms

2022-12-01 · Bruno Gavranović, Mattia Villani

We define the bicategory of Graph Convolutional Neural Networks $\mathbf{GCNN}_n$ for an arbitrary graph with $n$ nodes. We show it can be factored through the already existing categorical constructions for deep learning…

Inductive Bias

Median activation functions for graph neural networks

2018-10-29 · Luana Ruiz, Fernando Gama, Antonio G. Marques, Alejandro Ribeiro

Graph neural networks (GNNs) have been shown to replicate convolutional neural networks' (CNNs) superior performance in many problems involving graphs. By replacing regular convolutions with linear shift-invariant graph …