Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210221883> ?p ?o ?g. }
- W3210221883 abstract "For supervised learning with tabular data, decision tree ensembles produced via boosting techniques generally dominate real-world applications involving iid training/test sets. However for graph data where the iid assumption is violated due to structured relations between samples, it remains unclear how to best incorporate this structure within existing boosting pipelines. To this end, we propose a generalized framework for iterating boosting with graph propagation steps that share node/sample information across edges connecting related samples. Unlike previous efforts to integrate graph-based models with boosting, our approach is anchored in a principled meta loss function such that provable convergence can be guaranteed under relatively mild assumptions. Across a variety of non-iid graph datasets with tabular node features, our method achieves comparable or superior performance than both tabular and graph neural network models, as well as existing hybrid strategies that combine the two. Beyond producing better predictive performance than recently proposed graph models, our proposed techniques are easy to implement, computationally more efficient, and enjoy stronger theoretical guarantees (which make our results more reproducible)." @default.
- W3210221883 created "2021-11-08" @default.
- W3210221883 creator A5015179224 @default.
- W3210221883 creator A5016551629 @default.
- W3210221883 creator A5023028617 @default.
- W3210221883 creator A5032791121 @default.
- W3210221883 creator A5060687985 @default.
- W3210221883 creator A5074303284 @default.
- W3210221883 creator A5085016531 @default.
- W3210221883 date "2021-10-26" @default.
- W3210221883 modified "2023-10-14" @default.
- W3210221883 title "Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features" @default.
- W3210221883 cites W1546004968 @default.
- W3210221883 cites W1560724230 @default.
- W3210221883 cites W1678356000 @default.
- W3210221883 cites W1774304772 @default.
- W3210221883 cites W2116341502 @default.
- W3210221883 cites W2120391124 @default.
- W3210221883 cites W2154455818 @default.
- W3210221883 cites W2519887557 @default.
- W3210221883 cites W2768348081 @default.
- W3210221883 cites W2787740662 @default.
- W3210221883 cites W2900470550 @default.
- W3210221883 cites W2948000013 @default.
- W3210221883 cites W2949945331 @default.
- W3210221883 cites W2963326510 @default.
- W3210221883 cites W2964022491 @default.
- W3210221883 cites W2964091842 @default.
- W3210221883 cites W2967728833 @default.
- W3210221883 cites W2995914187 @default.
- W3210221883 cites W3004780002 @default.
- W3210221883 cites W3022208364 @default.
- W3210221883 cites W3035356236 @default.
- W3210221883 cites W3080555959 @default.
- W3210221883 cites W3088367830 @default.
- W3210221883 cites W3090999459 @default.
- W3210221883 cites W3091997330 @default.
- W3210221883 cites W3097264851 @default.
- W3210221883 cites W3100363647 @default.
- W3210221883 cites W3100400430 @default.
- W3210221883 cites W3100646853 @default.
- W3210221883 cites W3111356309 @default.
- W3210221883 cites W3114500711 @default.
- W3210221883 cites W3118310392 @default.
- W3210221883 cites W3121937977 @default.
- W3210221883 cites W3125667605 @default.
- W3210221883 cites W3129205570 @default.
- W3210221883 cites W3129794609 @default.
- W3210221883 cites W3133953674 @default.
- W3210221883 cites W3135514413 @default.
- W3210221883 cites W3135716056 @default.
- W3210221883 cites W3136305959 @default.
- W3210221883 cites W3139391937 @default.
- W3210221883 cites W3141595720 @default.
- W3210221883 cites W3152893301 @default.
- W3210221883 cites W3208180646 @default.
- W3210221883 cites W3021975806 @default.
- W3210221883 doi "https://doi.org/10.48550/arxiv.2110.13413" @default.
- W3210221883 hasPublicationYear "2021" @default.
- W3210221883 type Work @default.
- W3210221883 sameAs 3210221883 @default.
- W3210221883 citedByCount "0" @default.
- W3210221883 crossrefType "posted-content" @default.
- W3210221883 hasAuthorship W3210221883A5015179224 @default.
- W3210221883 hasAuthorship W3210221883A5016551629 @default.
- W3210221883 hasAuthorship W3210221883A5023028617 @default.
- W3210221883 hasAuthorship W3210221883A5032791121 @default.
- W3210221883 hasAuthorship W3210221883A5060687985 @default.
- W3210221883 hasAuthorship W3210221883A5074303284 @default.
- W3210221883 hasAuthorship W3210221883A5085016531 @default.
- W3210221883 hasBestOaLocation W32102218831 @default.
- W3210221883 hasConcept C119857082 @default.
- W3210221883 hasConcept C124101348 @default.
- W3210221883 hasConcept C132525143 @default.
- W3210221883 hasConcept C154945302 @default.
- W3210221883 hasConcept C169258074 @default.
- W3210221883 hasConcept C31972630 @default.
- W3210221883 hasConcept C3770464 @default.
- W3210221883 hasConcept C41008148 @default.
- W3210221883 hasConcept C46686674 @default.
- W3210221883 hasConcept C70153297 @default.
- W3210221883 hasConcept C80444323 @default.
- W3210221883 hasConceptScore W3210221883C119857082 @default.
- W3210221883 hasConceptScore W3210221883C124101348 @default.
- W3210221883 hasConceptScore W3210221883C132525143 @default.
- W3210221883 hasConceptScore W3210221883C154945302 @default.
- W3210221883 hasConceptScore W3210221883C169258074 @default.
- W3210221883 hasConceptScore W3210221883C31972630 @default.
- W3210221883 hasConceptScore W3210221883C3770464 @default.
- W3210221883 hasConceptScore W3210221883C41008148 @default.
- W3210221883 hasConceptScore W3210221883C46686674 @default.
- W3210221883 hasConceptScore W3210221883C70153297 @default.
- W3210221883 hasConceptScore W3210221883C80444323 @default.
- W3210221883 hasLocation W32102218831 @default.
- W3210221883 hasOpenAccess W3210221883 @default.
- W3210221883 hasPrimaryLocation W32102218831 @default.
- W3210221883 hasRelatedWork W3151529617 @default.
- W3210221883 hasRelatedWork W3159988495 @default.
- W3210221883 hasRelatedWork W3200719183 @default.
- W3210221883 hasRelatedWork W3204641204 @default.