Pairwise Alignment

Pairwise alignment is a technique used to compare and align pairs of data points, often within complex structures like graphs or images, to improve model performance and understanding. Current research focuses on applying pairwise alignment within various machine learning models, including graph neural networks and convolutional neural networks, to address challenges such as domain adaptation, link prediction, and semi-supervised learning. This approach is proving valuable in diverse fields, enhancing accuracy in tasks ranging from node classification in social networks to emotion recognition from EEG data and improving the efficiency of resource management in communication networks. The resulting improvements in model accuracy and interpretability are driving significant advancements across multiple scientific disciplines.

Papers

March 2, 2024

Pairwise Alignment Improves Graph Domain Adaptation
Shikun Liu, Deyu Zou, Han Zhao, Pan Li
Graph Domain Adaptation Pairwise Alignment Graph Based Method Graph Distribution Shift

October 17, 2023

LPFormer: An Adaptive Graph Transformer for Link Prediction
Harry Shomer, Yao Ma, Haitao Mao, Juanhui Li, Bo Wu, Jiliang Tang
Link Prediction Graph Transformer Graph Structured Data Message Passing Neural Network Pairwise Alignment

July 26, 2023

Entropy Neural Estimation for Graph Contrastive Learning
Yixuan Ma, Xiaolin Zhang, Peng Zhang, Kun Zhan
Contrastive Learning Loss Function Dimensional Embeddings Graph Encoder Pairwise Alignment Entropy Neural

January 20, 2023

Flex-Net: A Graph Neural Network Approach to Resource Management in Flexible Duplex Networks
Tharaka Perera, Saman Atapattu, Yuting Fang, Prathapasinghe Dharmawansa, Jamie Evans
Graph Neural Network Resource Allocation Resource Management Full Duplex Pairwise Alignment Rate Maximization

May 17, 2022

Pairwise Comparison Network for Remote Sensing Scene Classification
Zhang Yue, Zheng Xiangtao, Lu Xiaoqiang
Convolutional Neural Network Scene Classification Pairwise Learning Remote Sensing Scene Classification Pairwise Alignment

February 22, 2022

Message passing all the way up
Petar Veličković
Graph Neural Network Graph Drawing Graph Representation New Way System Message Input Graph Pairwise Alignment

February 11, 2022

PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition
Guangyi Zhang, Vandad Davoodnia, Ali Etemad
Emotion Recognition Meaningful Representation Document Parsing EEG Representation Pairwise Alignment

February 7, 2022

Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignment
Zhipeng Ding, Marc Niethammer
Image Registration Diffeomorphic Image Registration Pairwise Alignment Conditional Atlas Atlas Based Segmentation

November 17, 2021

Interpretable Models via Pairwise permutations algorithm
Troy Maaslandand, João Pereira, Diogo Bastos, Marcus de Goffau, Max Nieuwdorp, Aeilko H. Zwinderman, Evgeni Levin
Interpretable Model Feature Importance Permutation Importance Correlation Bias Pairwise Alignment