Order Neighbor

"Order neighbor" research broadly explores how information from a node's surrounding network influences its representation and behavior in various machine learning contexts, aiming to improve model accuracy and efficiency. Current research focuses on mitigating issues like over-smoothing in graph neural networks (GNNs) and improving the robustness of pseudo-label learning by carefully considering the quality and quantity of neighboring information, often employing techniques like contrastive learning and adaptive augmentation. These advancements have significant implications for diverse applications, including graph data analysis, person re-identification, and federated learning, by enhancing model performance and addressing limitations of existing methods.

Papers

November 7, 2024

Higher-Order GNNs Meet Efficiency: Sparse Sobolev Graph Neural Networks
Jhony H. Giraldo, Aref Einizade, Andjela Todorovic, Jhon A. Castro-Correa, Mohsen Badiey, Thierry Bouwmans, Fragkiskos D. Malliaros
Graph Neural Network Graph Signal Convolution Operator Order Neighbor Order Graph Neural Network

August 6, 2024

TSC: A Simple Two-Sided Constraint against Over-Smoothing
Furong Peng, Kang Liu, Xuan Lu, Yuhua Qian, Hongren Yan, Chao Ma
Graph Convolutional Network Node Representation Deeper Network Graph Convolutional Neural Network Undisciplined Over Smoothing Order Neighbor

May 9, 2024

Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
Xiangbo Yin, Jiangming Shi, Yachao Zhang, Yang Lu, Zhizhong Zhang, Yuan Xie, Yanyun Qu
Unsupervised Setting Pseudo Labeling Visible Infrared Person Re Identification Noisy Pseudo Label Robust Pseudo Label Label Calibration Order Neighbor

March 30, 2023

Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning
Chongjian Ge, Jiangliu Wang, Zhan Tong, Shoufa Chen, Yibing Song, Ping Luo
Contrastive Learning Contrastive Representation Learning Instance Level Label Positive Sentiment Order Neighbor Instance Correlation

January 26, 2023

Visiting Distant Neighbors in Graph Convolutional Networks
Alireza Hashemi, Hernan Makse
Deep Learning Graph Data Thy Neighbor Order Neighbor Neighboring Node

November 29, 2022

Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning
Zheren Fu, Zhendong Mao, Bo Hu, An-An Liu, Yongdong Zhang
Deep Metric Learning Metric Learning Loss Intra Class Variation Adaptive Augmentation Order Neighbor

July 30, 2022

Local Graph Embeddings Based on Neighbors Degree Frequency of Nodes
Vahid Shirbisheh
Node Embeddings Random Node Graph Machine Learning Graph Embeddings Directed Graph Centrality Measure Breadth First Order Neighbor

April 6, 2022

Greedier is Better: Selecting Multiple Neighbors per Iteration for Sparse Subspace Clustering
Jwo-Yuh Wu, Liang-Chi Huang, Wen-Hsuan Li, Chun-Hung Liu, Rung-Hung Gau
View Selection Neighborhood Selection Greedy SLIM Orthogonal Matching Pursuit Order Neighbor

March 23, 2022

Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching
Zexi Li, Jiaxun Lu, Shuang Luo, Didi Zhu, Yunfeng Shao, Yinchuan Li, Zhimeng Zhang, Yongheng Wang, Chao Wu
Peer to Peer Client Heterogeneity Clustered Federated Learning Order Neighbor Neighbor Correspondence Matching

March 19, 2022

Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Jie Chen, Shouzhen Chen, Junbin Gao, Zengfeng Huang, Junping Zhang, Jian Pu
Graph Drawing Graph Convolution Heterophilic Graph Graph Convolution Network GNN Framework Order Neighbor

December 14, 2021

On Improving Resource Allocations by Sharing
Robert Bredereck, Andrzej Kaczmarczyk, Junjie Luo, Rolf Niedermeier, Florian Sachse
Resource Allocation Egalitarian Fairness Order Neighbor

Order Neighbor

Papers

Higher-Order GNNs Meet Efficiency: Sparse Sobolev Graph Neural Networks

TSC: A Simple Two-Sided Constraint against Over-Smoothing

Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification

Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning

Visiting Distant Neighbors in Graph Convolutional Networks

Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning

Local Graph Embeddings Based on Neighbors Degree Frequency of Nodes

Greedier is Better: Selecting Multiple Neighbors per Iteration for Sparse Subspace Clustering

Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching

Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily

On Improving Resource Allocations by Sharing