Waqar Ali

Waqar Ali

Auto-generated profile, based on publicly available information

Waqar Ali

Ca’ Foscari University of Venice

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 September 2024 in Pattern Recognition Letters
Verified
Journal Article
Closed access
WAWaqar Ali
Waqar Ali
SVSebastiano Vascon
Sebastiano Vascon
TSThilo Stadelmann
Thilo Stadelmann
MPMarcello Pelillo
Marcello Pelillo

27 March 2023
Verified
Conference Paper
Open access
WAWaqar Ali
Waqar Ali
SVSebastiano Vascon
Sebastiano Vascon
Thilo StadelmannThilo Stadelmann
Thilo Stadelmann
MPMarcello Pelillo
Marcello Pelillo
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.

22 November 2025 in Pattern Recognition
Verified
Journal Article
Open access
WAWaqar Ali
Waqar Ali
SVSebastiano Vascon
Sebastiano Vascon
Thilo StadelmannThilo Stadelmann
Thilo Stadelmann
MPMarcello Pelillo
Marcello Pelillo

15 October 2026 in Expert Systems with Applications
Verified
Journal Article
Open access
WAWaqar Ali
Waqar Ali
ABAhmed Begga
Ahmed Begga
SVSebastiano Vascon
Sebastiano Vascon
FEFrancisco Escolano
Francisco Escolano
Miguel Angel LozanoMiguel Angel Lozano
Miguel Angel Lozano
MPMarcello Pelillo
Marcello Pelillo

3 November 2017
Verified
Book Chapter
Closed access
PDF file
ASArje Saba
Arje Saba
AKAdia Khalid
Adia Khalid
AIAdnan Ishaq
Adnan Ishaq
KPKomal Parvez
Komal Parvez
SASayed Aimal
Sayed Aimal
Nadeem JavaidNadeem Javaid
Nadeem Javaid

31 January 2025
Verified
Book Chapter
Closed access
PDF file
ABAhmed Begga
Ahmed Begga
WAWaqar Ali
Waqar Ali
GNGabriel Niculescu
Gabriel Niculescu
FEFrancisco Escolano
Francisco Escolano
Thilo StadelmannThilo Stadelmann
Thilo Stadelmann
MPMarcello Pelillo
Marcello Pelillo