Waqar Ali
Waqar Ali has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Marcello Pelillo
Università Ca' Foscari Venezia, Venice, Italy and Zhejiang Normal University, Jinhua, China
4 shared publications - Thilo Stadelmann
Centre for Artificial Intelligence, Zurich University of Applied Sciences, Winterthur, Switzerland
4 shared publications - Sebastiano Vascon
Department of Environmental Sciences, Informatics and Statistics, Ca' Foscari University of Venice, Venice, Italy
3 shared publications - Ahmed Begga
Department of Computer Science and Artificial Intelligence, University of Alicante, 03690 Alicante, Spain
2 shared publications - Francisco Escolano
Department of Computer Science and Artificial Intelligence, University of Alicante, 03690 Alicante, Spain
2 shared publications - Adia Khalid
Department of Computer Science, COMSATS University Islamabad, Islamabad 44000, Pakistan
1 shared publication
Latest Publications
- Open Access
- 15 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Learnable eigenfunctions for graph rewiring: Balancing local community structure and global connectivity
- 15 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Open AccessLearnable eigenfunctions for graph rewiring: Balancing local community structure and global connectivity
- Open Access
- 22 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Multi-view graph pooling via dominant sets for graph classification
- 22 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Open AccessMulti-view graph pooling via dominant sets for graph classification
- 31 January 2025
- Published by Springer Nature
- p. 21-30
Community-Hop: Enhancing Node Classification Through Community Preference
- 31 January 2025
- Published by Springer Nature
- p. 21-30
Community-Hop: Enhancing Node Classification Through Community Preference
- 13 September 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 186, 71-77
Hierarchical Glocal Attention Pooling for Graph Classification
- 13 September 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 186, 71-77
Hierarchical Glocal Attention Pooling for Graph Classification
- Open Access
- 27 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 544-552
Quasi-CliquePool: Hierarchical Graph Pooling for Graph Classification
Graph Neural Networks (GNNs) have revolutionized graph learning through efficiently learned node embeddings and achieved promising results in various graph-related tasks such as node and graph classification. Within GNNs, a pooling operation reduces the size of the input graph by grouping nodes that share commonalities intending to generate more robust and expressive latent representations. For this reason, pooling is a critical operation that significantly affects downstream tasks. Existing global pooling methods mostly use readout functions like max or sum to perform the pooling operations, but these methods neglect the hierarchical information of graphs. Clique-based hierarchical pooling methods have recently been developed to overcome global pooling issues. Such clique pooling methods perform a hard partition between nodes, which destroys the topological structural relationship of nodes, assuming that a node should belong to a single cluster. However, overlapping clusters widely exist in many real-world networks since a node can belong to more than one cluster. Here we introduce a new hierarchical graph pooling method to address this issue. Our pooling method, named Quasi-CliquePool, builds on the concept of a quasi-clique, which generalizes the notion of cliques to extract dense incomplete subgraphs of a graph. We also introduce a soft peel-off strategy to find the overlapping cluster nodes to keep the topological structural relationship of nodes. For a fair comparison, we follow the same procedure and training settings used by state-of-the-art pooling techniques. Our experiments demonstrate that combining the Quasi-Clique Pool with existing GNN architectures yields an average improvement of 2% accuracy on four out of six graph classification benchmarks compared to other existing pooling methods.
- 27 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 544-552
Open AccessQuasi-CliquePool: Hierarchical Graph Pooling for Graph Classification
Graph Neural Networks (GNNs) have revolutionized graph learning through efficiently learned node embeddings and achieved promising results in various graph-related tasks such as node and graph classification. Within GNNs, a pooling operation reduces the size of the input graph by grouping nodes that share commonalities intending to generate more robust and expressive latent representations. For this reason, pooling is a critical operation that significantly affects downstream tasks. Existing global pooling methods mostly use readout functions like max or sum to perform the pooling operations, but these methods neglect the hierarchical information of graphs. Clique-based hierarchical pooling methods have recently been developed to overcome global pooling issues. Such clique pooling methods perform a hard partition between nodes, which destroys the topological structural relationship of nodes, assuming that a node should belong to a single cluster. However, overlapping clusters widely exist in many real-world networks since a node can belong to more than one cluster. Here we introduce a new hierarchical graph pooling method to address this issue. Our pooling method, named Quasi-CliquePool, builds on the concept of a quasi-clique, which generalizes the notion of cliques to extract dense incomplete subgraphs of a graph. We also introduce a soft peel-off strategy to find the overlapping cluster nodes to keep the topological structural relationship of nodes. For a fair comparison, we follow the same procedure and training settings used by state-of-the-art pooling techniques. Our experiments demonstrate that combining the Quasi-Clique Pool with existing GNN architectures yields an average improvement of 2% accuracy on four out of six graph classification benchmarks compared to other existing pooling methods.
- 3 November 2017
- Published by Springer Nature
- p. 26-36
Home Energy Management Using Social Spider and Bacterial Foraging Algorithm
- 3 November 2017
- Published by Springer Nature
- p. 26-36
Home Energy Management Using Social Spider and Bacterial Foraging Algorithm