Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386401977> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4386401977 endingPage "571" @default.
- W4386401977 startingPage "559" @default.
- W4386401977 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 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." @default.
- W4386401977 created "2023-09-04" @default.
- W4386401977 creator A5004075655 @default.
- W4386401977 creator A5021920057 @default.
- W4386401977 creator A5046809753 @default.
- W4386401977 creator A5060042752 @default.
- W4386401977 creator A5074672983 @default.
- W4386401977 creator A5076426962 @default.
- W4386401977 creator A5085309099 @default.
- W4386401977 date "2023-10-01" @default.
- W4386401977 modified "2023-10-18" @default.
- W4386401977 title "On exploring node-feature and graph-structure diversities for node drop graph pooling" @default.
- W4386401977 cites W1849277567 @default.
- W4386401977 cites W1965555277 @default.
- W4386401977 cites W2027482274 @default.
- W4386401977 cites W2060630644 @default.
- W4386401977 cites W2130354913 @default.
- W4386401977 cites W2345701984 @default.
- W4386401977 cites W2565330852 @default.
- W4386401977 cites W2594183968 @default.
- W4386401977 cites W2788919350 @default.
- W4386401977 cites W2963066159 @default.
- W4386401977 cites W2963555845 @default.
- W4386401977 cites W2964544183 @default.
- W4386401977 cites W2983288276 @default.
- W4386401977 cites W2997997679 @default.
- W4386401977 cites W3003393086 @default.
- W4386401977 cites W3133780103 @default.
- W4386401977 cites W3142570770 @default.
- W4386401977 cites W3156414040 @default.
- W4386401977 cites W3157110956 @default.
- W4386401977 cites W3173856251 @default.
- W4386401977 cites W3183241772 @default.
- W4386401977 cites W3200094660 @default.
- W4386401977 cites W3206856212 @default.
- W4386401977 cites W3208074551 @default.
- W4386401977 cites W4220742022 @default.
- W4386401977 cites W4283377296 @default.
- W4386401977 cites W4295105988 @default.
- W4386401977 cites W4296821948 @default.
- W4386401977 cites W4301430669 @default.
- W4386401977 cites W4327652436 @default.
- W4386401977 cites W4385123872 @default.
- W4386401977 doi "https://doi.org/10.1016/j.neunet.2023.08.046" @default.
- W4386401977 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37696073" @default.
- W4386401977 hasPublicationYear "2023" @default.
- W4386401977 type Work @default.
- W4386401977 citedByCount "0" @default.
- W4386401977 crossrefType "journal-article" @default.
- W4386401977 hasAuthorship W4386401977A5004075655 @default.
- W4386401977 hasAuthorship W4386401977A5021920057 @default.
- W4386401977 hasAuthorship W4386401977A5046809753 @default.
- W4386401977 hasAuthorship W4386401977A5060042752 @default.
- W4386401977 hasAuthorship W4386401977A5074672983 @default.
- W4386401977 hasAuthorship W4386401977A5076426962 @default.
- W4386401977 hasAuthorship W4386401977A5085309099 @default.
- W4386401977 hasConcept C132525143 @default.
- W4386401977 hasConcept C154945302 @default.
- W4386401977 hasConcept C41008148 @default.
- W4386401977 hasConcept C70437156 @default.
- W4386401977 hasConcept C80444323 @default.
- W4386401977 hasConceptScore W4386401977C132525143 @default.
- W4386401977 hasConceptScore W4386401977C154945302 @default.
- W4386401977 hasConceptScore W4386401977C41008148 @default.
- W4386401977 hasConceptScore W4386401977C70437156 @default.
- W4386401977 hasConceptScore W4386401977C80444323 @default.
- W4386401977 hasLocation W43864019771 @default.
- W4386401977 hasLocation W43864019772 @default.
- W4386401977 hasOpenAccess W4386401977 @default.
- W4386401977 hasPrimaryLocation W43864019771 @default.
- W4386401977 hasRelatedWork W147410782 @default.
- W4386401977 hasRelatedWork W2626256601 @default.
- W4386401977 hasRelatedWork W2748952813 @default.
- W4386401977 hasRelatedWork W2899084033 @default.
- W4386401977 hasRelatedWork W2900413183 @default.
- W4386401977 hasRelatedWork W2953234277 @default.
- W4386401977 hasRelatedWork W3015684221 @default.
- W4386401977 hasRelatedWork W3022252430 @default.
- W4386401977 hasRelatedWork W4287804464 @default.
- W4386401977 hasRelatedWork W4287816705 @default.
- W4386401977 hasVolume "167" @default.
- W4386401977 isParatext "false" @default.
- W4386401977 isRetracted "false" @default.
- W4386401977 workType "article" @default.