Back to Search
Start Over
On exploring node-feature and graph-structure diversities for node drop graph pooling.
- Source :
-
Neural Networks . Oct2023, Vol. 167, p559-571. 13p. - Publication Year :
- 2023
-
Abstract
- Graph Neural Networks (GNNs) have been successfully applied to graph-level tasks in various fields such as biology, social networks, computer vision, and natural language processing. For the graph-level representations learning of GNNs, graph pooling plays an essential role. Among many pooling techniques, node drop pooling has garnered significant attention and is considered as a leading approach. However, existing node drop pooling methods, which typically retain the top-k nodes based on their significance scores, often overlook the diversity inherent in node features and graph structures. This limitation leads to suboptimal graph-level representations. To overcome this, we introduce a groundbreaking plug-and-play score scheme, termed MID. MID comprises a M ultidimensional score space and two key operations: fl I pscore and D ropscore. The multidimensional score space depicts the significance of nodes by multiple criteria; the flipscore process promotes the preservation of distinct node features; the dropscore compels the model to take into account a range of graph structures rather than focusing on local structures. To evaluate the effectiveness of our proposed MID, we have conducted extensive experiments by integrating it with a broad range of recent node drop pooling methods, such as TopKPool, SAGPool, GSAPool, and ASAP. In particular, MID has proven to bring a significant average improvement of approximately 2.8% over the four aforementioned methods when tested on 17 real-world graph classification datasets. Code is available at https://github.com/whuchuang/mid. [ABSTRACT FROM AUTHOR]
- Subjects :
- *COMPUTER vision
*SOCIAL networks
*NATURAL language processing
Subjects
Details
- Language :
- English
- ISSN :
- 08936080
- Volume :
- 167
- Database :
- Academic Search Index
- Journal :
- Neural Networks
- Publication Type :
- Academic Journal
- Accession number :
- 173010397
- Full Text :
- https://doi.org/10.1016/j.neunet.2023.08.046