born in 1995. PhD candidate. Student member of CCF. Her main research interest includes the optimization of graph neural network models and the explainability
born in 1997. PhD candidate. Student member of CCF. His main research interests include graph neural networks, graph self-supervised learning, and graph neural network architecture search and robustness on graph learning. (songshuhan19s@ict.ac.cn)
born in 1990. PhD candidate. Member of CCF. Her main research interests include graph processing and parallel computing. (zhangyuan-ams@ict.ac.cn)
born in 1989. PhD, associate professor. Member of CCF. His main research interests include parallel computing and high throughput computing architecture
born in 1981. PhD, professor. Member of CCF. His main research interests include algorithm paralleling and optimizing, software simulation, and architecture for high throughput computer. (yexiaochun@ict.ac.cn)
born in 1966. PhD, professor. Senior member of CCF. His main research interests include high performance computer architecture, processor design, and digital signal processing. (tang@ict.ac.cn)
In recent years, with the extensive application of graph neural network (GNN) technology in the fields such as social network, information, chemistry and biology, the interpretability of GNN has attracted widespread attention. However, prevailing explanation methods fail to capture the hierarchical explanation information, and these hierarchical information has not been fully utilized to improve the classification accuracy of graph tasks. To address this issue, we propose a hierarchical self-explanation graph representation learning model called HSEGRL (hierarchical self-explanation graph representation learning). This model, by discovering hierarchical information in the graph structure, predicts graph classifications while outputting hierarchical self-explanation results. Specifically, we design the basic unit for extracting hierarchical information—interpreters. These interpreters consist of an encoder that extracts node features, a pooling layer that perceives hierarchical explanation-aware subgraphs, and a decoder that refines higher-order explanation information. We refine the pooling mechanism with an explanation-aware strategy, enabling the hierarchical selection of subgraphs based on the evaluation of the model’s topology and feature importance, thereby facilitating hierarchical self-explanation in conjunction with graph classification. HSEGRL is a functionally comprehensive and transferable self-explanatory graph representation learning framework that can hierarchically consider the model’s topological information and node feature information. We conduct extensive experiments on datasets from molecular, protein, and social network, and demonstrate that HSEGRL surpasses existing advanced self-explanatory graph neural network models and graph neural network models in terms of graph classification performance. Furthermore, the visualization of layered explanation outcomes substantiates the credibility of our proposed explanation methodology.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |