Pooling Operator

Pooling operators are crucial components in various neural network architectures, aiming to reduce dimensionality and aggregate information from multiple sources while preserving essential features. Current research focuses on developing more efficient and effective pooling methods for diverse data types, including graphs and images, with a particular emphasis on improving accuracy, robustness, and interpretability. This involves exploring novel algorithms like those based on minimum description length principles, convex relaxations, and fuzzy logic, as well as designing architectures that adaptively determine optimal pooling parameters. These advancements have significant implications for improving the performance and efficiency of deep learning models across numerous applications, from image processing and graph classification to knowledge graph reasoning.

Papers

September 16, 2024

Hierarchical Graph Pooling Based on Minimum Description Length
Jan von Pichowski, Christopher Blöcker, Ingo Scholtes
Community Detection Graph Pooling Graph Classification Datasets Pooling Operator

June 27, 2024

CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network
Jia-Hau Bai, Chi-Ting Liu, Yu Wang, Fu-Chieh Chang, Pei-Yuan Wu
Convolutional Neural Network Dual Network Soft Cap Pooling Operator Adversarial Polytope

February 3, 2024

SemPool: Simple, robust, and interpretable KG pooling for enhancing language models
Costas Mavromatis, Petros Karypis, George Karypis
Language Model Graph Neural Network Knowledge Graph Graph Pooling Pooling Operator

August 7, 2023

Optimal Approximation and Learning Rates for Deep Convolutional Neural Networks
Shao-Bo Lin
Deep Convolutional Neural Network Learning Rate Average Approximation Approximation Rate Pooling Operator

June 22, 2023

On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
Chuang Liu, Yibing Zhan, Baosheng Yu, Liu Liu, Bo Du, Wenbin Hu, Tongliang Liu
Graph Representation Node Feature Pooling Operator Diverse Graph Graph Pooling Method Graph Level Representation Learning

May 27, 2023

DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images
Hui Li, Yongbiao Xiao, Chunyang Cheng, Zhongwei Shen, Xiaoning Song
Multi Scale Image Fusion Fusion Network Richer RGB Infrared Feature Fusion Method Visible Image Fusion Visible Image Pooling Operator

April 4, 2023

The expressive power of pooling in Graph Neural Networks
Filippo Maria Bianchi, Veronica Lachi
Graph Neural Network Pooling Layer Expressive Power Graph Pooling Pooling Operator

March 10, 2023

Enhancing the accuracies by performing pooling decisions adjacent to the output layer
Yuval Meir, Yarden Tzach, Ronit D. Gross, Ofek Tevet, Roni Vardi, Ido Kanter
Decision Relevant Information Deep Architecture Linear Neural Network High Accuracy Last Layer Layer Output Pooling Operator

October 11, 2022

Embeddings as Epistemic States: Limitations on the Use of Pooling Operators for Accumulating Knowledge
Steven Schockaert
Jina Embeddings Knowledge Based Fundamental Limitation Epistemic State Pooling Operator Non Negative Knowledge Pooling

September 16, 2022

SPGP: Structure Prototype Guided Graph Pooling
Sangseon Lee, Dohoon Lee, Yinhua Piao, Sun Kim
Graph Representation Pooling Operator Graph Pooling Method Graph Classification Benchmark

September 7, 2022

Grouping-matrix based Graph Pooling with Adaptive Number of Clusters
Sung Moon Ko, Sungjun Cho, Dae-Woong Jeong, Sehui Han, Moontae Lee, Honglak Lee
Different Cluster Pooling Layer Graph Pooling Molecular Property Prediction Task Pooling Operator Differentiable Graph

September 4, 2022

Communication Efficient Distributed Learning over Wireless Channels
Idan Achituve, Wenbo Wang, Ethan Fetaya, Amir Leshem
LeArning Abstract Wireless Network Learning Framework Communication Efficiency Learning Model Wireless Channel Max Pooling Pooling Operator

February 12, 2022

Fuzzy Pooling
Dimitrios E. Diamantis, Dimitris K. Iakovidis
Convolutional Neural Network Max Pooling Pooling Operator