Siamese Graph

Siamese graph networks are a class of neural network architectures designed to compare and learn relationships between pairs of graph-structured data. Current research focuses on improving efficiency and accuracy in various applications, employing techniques like graph condensation to handle large graphs and incorporating node and edge features for enhanced representation learning. These networks are proving valuable in diverse fields, including drug discovery (predicting molecule-target interactions), optimization problems (improving branch-and-bound algorithms), and biometric authentication (iris recognition), demonstrating their broad applicability and potential to advance these areas. The development of more efficient and robust Siamese graph networks is a significant area of ongoing research.

Papers

May 22, 2024

Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition
Xinyi Gao, Tong Chen, Wentao Zhang, Junliang Yu, Guanhua Ye, Quoc Viet Hung Nguyen, Hongzhi Yin
Constructive Approach Large Scale Graph Graph Condensation Class Separation Class Node Siamese Graph

February 2, 2023

Predicting Molecule-Target Interaction by Learning Biomedical Network and Molecule Representations
Jinjiang Guo, Jie Li
Molecular Representation Molecular Information Biomedical Network Target Interaction Siamese Graph

October 30, 2022

Learning to Compare Nodes in Branch and Bound with Graph Neural Networks
Abdel Ghani Labassi, Didier Chételat, Andrea Lodi
LeArning Abstract Graph Neural Network Random Node Multi Channel Branch Node Similarity Bipartite Graph Branch and Bound Siamese Graph

August 10, 2022

Path-aware Siamese Graph Neural Network for Link Prediction
Jingsong Lv, Zhao Li, Hongyang Chen, Yao Qi, Chunqi Wu
Multi Task Link Prediction Self Supervised Contrastive Learning Siamese Graph

July 28, 2022

Verification system based on long-range iris and Graph Siamese Neural Networks
Francesco Zola, Jose Alvaro Fernandez-Carrasco, Jan Lukas Bruse, Mikel Galar, Zeno Geradts
Long Range Physiological Biometrics Biometric System Iris Recognition Verification Framework Siamese Graph

Siamese Graph

Papers

Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition

Predicting Molecule-Target Interaction by Learning Biomedical Network and Molecule Representations

Learning to Compare Nodes in Branch and Bound with Graph Neural Networks

Path-aware Siamese Graph Neural Network for Link Prediction

Verification system based on long-range iris and Graph Siamese Neural Networks