Please wait ...
0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
HiCAP: Hierarchical Clustering-based Attention Pooling for Graph Representation Learning
Authors :
Parsa Haddadian
1
Rooholah Abedian
2
Ali Moeini
3
1- Department of engineering science, college of engineering, University of Tehran
2- Faculty of Engineering Science, College of Engineering University of Tehran
3- Faculty of Engineering Science, College of Engineering University of Tehran
Keywords :
Graph Classification،Graph Neural Network (GNNs)،Graph Pooling،Deep Learning
Abstract :
Graph representation learning has gained increasing importance in the analysis of complex relational data. The utilization of Graph Neural Networks (GNNs) has demonstrated significant potential for capturing graph structures and node features in this domain. However, the challenge of graph pooling, which involves summarizing graphs into concise representations, remains a persistent obstacle. In this study, a novel method called HiCAP (Hierarchical Cluster-Based Attention Pooling) is proposed to address the limitations of existing graph pooling approaches. By combining the strengths of node clustering and node dropping techniques, HiCAP establishes a hierarchical framework. Initially, a soft cluster assignment matrix is learned through the application of a GNN. Subsequently, the matrix undergoes a transformation into a hard assignment by incorporating structural considerations. Attention-based scoring is subsequently employed to select representative nodes within each cluster. Extensive experimental evaluations on benchmark datasets showcase the effectiveness of HiCAP in graph classification tasks, outperforming state-of-the-art baselines. This method introduces an innovative approach to graph representation learning, thereby advancing graph pooling techniques.
Papers List
List of archived papers
TriMAE: Fashion visual search with Triplet Masked Auto Encoder Vision Transformer
Lachin Zamani - Reza Azmi
Attention-Boosted Ensemble of Pre-trained Convolutional Neural Networks for Accurate Diabetic Retinopathy Detection
Benyamin Mirab Golkhatmi - Mohammad Hossein Moattar
Joint mobility-aware offloading and UAV position optimization in Blockchain-enabled 5G
Zeinab Rabbani - Zeinab Movahedi
Towards Efficient Capsule Networks through Approximate Squash Function and Layer-wise Quantization
Mohsen Raji - Kimia Soroush - Amir Ghazizadeh
Enhancing Cloud Security with Federated CNN-LSTM: A Novel Approach to Intrusion Detection
Reyhaneh Ilaghi - Raheleh Ilaghi - Fereshteh Rahmani - Seyyed hamid Ghafoori
A New Application of Machine Learning Based Methods for Disk Space Variation Fault Diagnosis in Transformer Windings
Reza Behkam - Amir Lotfi - Gevork B. Gharehpetian
The Effect of Network Environment on Traffic Classification
Abolghasem Rezaei Khesal - Mehdi Teimouri
Evaluation of Efficient Electrocardiomatrix-based Identification Using Deep Learning Methods
Amirhossein Safari - Narges Mokhtari - Mohsen Hooshmand - Sadegh Sadeghi - Peyman Pahlevani
A Deep Reinforcement Learning Approach Combining Technical and Fundamental Analyses with a Large Language Model for Stock Trading
Mahan Veisi - Sadra Berangi - Mahdi Shahbazi Khojasteh - Armin Salimi-Badr
Averting Mode Collapse for Generative Zero-Shot Learning
Shayan Ramazi - Setare Shabani
more
Samin Hamayesh - Version 46.0.2