.png){kind=icon}
Return
On exploring node-feature and graph-structure diversities for node drop graph pooling
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2023.08.046.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 Multidimensional score space and two key operations: flIpscore and Dropscore. 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.(c) 2023 Elsevier Ltd. All rights reserved.
Keywords:
Graph neural networks
Graph pooling
Graph classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
8.2K
Citations:
3.0W
Organization
Cited Papers
ShareSaveNumerical investigation and sensitivity analysis of MHD ternary nanofluid flow between perforated squeezed Riga plates under the surveillance of microcantilever sensor.png)
AIP Advances
OAAI
AIP AdvancesIF0
OAAIShareSaveShareSaveShareSaveShareSaveAdmixture Effects on the Rheological/Mechanical Behavior and Micro-Structure Evolution of Alkali-Activated Slag BackfillsMineralsOAAI
MineralsIF0
OAAIShareSaveShareSaveEnhancing Graph Neural Networks by a High-quality Aggregation of Beneficial InformationNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
ShareSaveShareSave
View more