Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206860349> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4206860349 abstract "Finding the seed set that maximizes the influence spread over a network is a well-known NP-hard problem. Though a greedy algorithm can provide near-optimal solutions, the subproblem of influence estimation renders the solutions inefficient. In this work, we propose textsc{Glie}, a graph neural network that learns how to estimate the influence spread of the independent cascade. GLIE relies on a theoretical upper bound that is tightened through supervised training.Experiments indicate that it provides accurate influence estimation for real graphs up to 10 times larger than the train set.Subsequently, we incorporate it into three influence maximization techniques.We first utilize Cost Effective Lazy Forward optimization substituting Monte Carlo simulations with GLIE, surpassing the benchmarks albeit with a computational overhead. To improve computational efficiency we first devise a Q-learning method that learns to choose seeds sequentially using GLIE's predictions. Finally, we arrive at the most efficient approach by developing a provably submodular influence spread based on GLIE's representations, to rank nodes while building the seed set adaptively. The proposed algorithms are inductive, meaning they are trained on graphs with less than 300 nodes and up to 5 seeds, and tested on graphs with millions of nodes and up to 200 seeds. The final method exhibits the most promising combination of time efficiency and influence quality, outperforming several baselines." @default.
- W4206860349 created "2022-01-25" @default.
- W4206860349 creator A5057695979 @default.
- W4206860349 creator A5079375197 @default.
- W4206860349 creator A5083139588 @default.
- W4206860349 creator A5087251228 @default.
- W4206860349 date "2021-08-10" @default.
- W4206860349 modified "2023-10-13" @default.
- W4206860349 title "Maximizing Influence with Graph Neural Networks" @default.
- W4206860349 doi "https://doi.org/10.48550/arxiv.2108.04623" @default.
- W4206860349 hasPublicationYear "2021" @default.
- W4206860349 type Work @default.
- W4206860349 citedByCount "0" @default.
- W4206860349 crossrefType "posted-content" @default.
- W4206860349 hasAuthorship W4206860349A5057695979 @default.
- W4206860349 hasAuthorship W4206860349A5079375197 @default.
- W4206860349 hasAuthorship W4206860349A5083139588 @default.
- W4206860349 hasAuthorship W4206860349A5087251228 @default.
- W4206860349 hasBestOaLocation W42068603491 @default.
- W4206860349 hasConcept C111919701 @default.
- W4206860349 hasConcept C11413529 @default.
- W4206860349 hasConcept C119857082 @default.
- W4206860349 hasConcept C122818955 @default.
- W4206860349 hasConcept C126255220 @default.
- W4206860349 hasConcept C132525143 @default.
- W4206860349 hasConcept C154945302 @default.
- W4206860349 hasConcept C177264268 @default.
- W4206860349 hasConcept C178621042 @default.
- W4206860349 hasConcept C199360897 @default.
- W4206860349 hasConcept C2776330181 @default.
- W4206860349 hasConcept C2779960059 @default.
- W4206860349 hasConcept C33923547 @default.
- W4206860349 hasConcept C41008148 @default.
- W4206860349 hasConcept C50644808 @default.
- W4206860349 hasConcept C51823790 @default.
- W4206860349 hasConcept C80444323 @default.
- W4206860349 hasConceptScore W4206860349C111919701 @default.
- W4206860349 hasConceptScore W4206860349C11413529 @default.
- W4206860349 hasConceptScore W4206860349C119857082 @default.
- W4206860349 hasConceptScore W4206860349C122818955 @default.
- W4206860349 hasConceptScore W4206860349C126255220 @default.
- W4206860349 hasConceptScore W4206860349C132525143 @default.
- W4206860349 hasConceptScore W4206860349C154945302 @default.
- W4206860349 hasConceptScore W4206860349C177264268 @default.
- W4206860349 hasConceptScore W4206860349C178621042 @default.
- W4206860349 hasConceptScore W4206860349C199360897 @default.
- W4206860349 hasConceptScore W4206860349C2776330181 @default.
- W4206860349 hasConceptScore W4206860349C2779960059 @default.
- W4206860349 hasConceptScore W4206860349C33923547 @default.
- W4206860349 hasConceptScore W4206860349C41008148 @default.
- W4206860349 hasConceptScore W4206860349C50644808 @default.
- W4206860349 hasConceptScore W4206860349C51823790 @default.
- W4206860349 hasConceptScore W4206860349C80444323 @default.
- W4206860349 hasLocation W42068603491 @default.
- W4206860349 hasOpenAccess W4206860349 @default.
- W4206860349 hasPrimaryLocation W42068603491 @default.
- W4206860349 hasRelatedWork W2402949237 @default.
- W4206860349 hasRelatedWork W2594118609 @default.
- W4206860349 hasRelatedWork W2766474417 @default.
- W4206860349 hasRelatedWork W2896347948 @default.
- W4206860349 hasRelatedWork W2915041254 @default.
- W4206860349 hasRelatedWork W2950500962 @default.
- W4206860349 hasRelatedWork W2964314169 @default.
- W4206860349 hasRelatedWork W2968699064 @default.
- W4206860349 hasRelatedWork W3204684126 @default.
- W4206860349 hasRelatedWork W4302557420 @default.
- W4206860349 isParatext "false" @default.
- W4206860349 isRetracted "false" @default.
- W4206860349 workType "article" @default.