| Title | Structure-Aware Hierarchical Graph Pooling using Information Bottleneck |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Roy, Kashob Kumar, Roy, Amit, Mahbubur Rahman, A K M, Amin, M Ashraful, Ali, Amin Ahsan |
| Conference Name | 2021 International Joint Conference on Neural Networks (IJCNN) |
| Keywords | Attack Graphs, Benchmark testing, codes, composability, Data models, graph classification, graph neural networks, Graph Pooling, Information bottleneck, Perturbation methods, Predictive Metrics, pubcrawl, Resiliency, Robustness, Stability analysis |
| Abstract | 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. |
| DOI | 10.1109/IJCNN52387.2021.9533778 |
| Citation Key | roy_structure-aware_2021 |
Structure-Aware Hierarchical Graph Pooling using Information Bottleneck