paper-with-me

Papers

Maximal Independent Sets for Pooling in Graph Neural Networks

2023-07-24 · Stevan Stanovic, Benoit Gaüzère, Luc Brun

Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling.

📄 PDF Abstract BibTeX arXiv:2307.13011

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Maximal Independent Vertex Set applied to Graph Pooling

2022-08-02 · Stevan Stanovic, Benoit Gaüzère, Luc Brun

Convolutional neural networks (CNN) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete grid into a reduced grid with the same…

Graph Classificationimage-classificationImage Classification

Edge-Based Graph Component Pooling

2024-09-18 · T. Snelleman, B. M. Renting, H. H. Hoos, J. N. van Rijn

Graph-structured data naturally occurs in many research fields, such as chemistry and sociology. The relational information contained therein can be leveraged to statistically model graph properties through geometrical d…

Sociology

Path Integral Based Convolution and Pooling for Heterogeneous Graph Neural Networks

2023-02-26 · Lingjie Kong, Yun Liao

Graph neural networks (GNN) extends deep learning to graph-structure dataset. Similar to Convolutional Neural Networks (CNN) using on image prediction, convolutional and pooling layers are the foundation to success for G…

Prediction

Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks

2021-07-03 · Amirhossein Nouranizadeh, Mohammadjavad Matinkia, Mohammad Rahmati, Reza Safabakhsh

In this paper, we propose a novel pooling layer for graph neural networks based on maximizing the mutual information between the pooled graph and the input graph. Since the maximum mutual information is difficult to comp…

Combinatorial OptimizationGraph ClassificationGraph Neural NetworkInductive Bias

Maximal function pooling with applications

2021-03-01 · Wojciech Czaja, Weilin Li, Yiran Li, Mike Pekala

Inspired by the Hardy-Littlewood maximal function, we propose a novel pooling strategy which is called maxfun pooling. It is presented both as a viable alternative to some of the most popular pooling functions, such as m…

image-classificationImage Classification