Visible to the public Biblio

Filters: Author is Roy, Kashob Kumar  [Clear All Filters]
2022-01-10
Roy, Kashob Kumar, Roy, Amit, Mahbubur Rahman, A K M, Amin, M Ashraful, Ali, Amin Ahsan.  2021.  Structure-Aware Hierarchical Graph Pooling using Information Bottleneck. 2021 International Joint Conference on Neural Networks (IJCNN). :1–8.
Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling and summarizing nodes' features in a graph. However, most existing pooling methods are unable to capture distinguishable structural information effectively. Besides, they are prone to adversarial attacks. In this work, we propose a novel pooling method named as HIBPool where we leverage the Information Bottleneck (IB) principle that optimally balances the expressiveness and robustness of a model to learn representations of input data. Furthermore, we introduce a novel structure-aware Discriminative Pooling Readout (DiP-Readout) function to capture the informative local subgraph structures in the graph. Finally, our experimental results show that our model significantly outperforms other state-of-art methods on several graph classification benchmarks and more resilient to feature-perturbation attack than existing pooling methods11Source code at: https://github.com/forkkr/HIBPool.