Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317884041> ?p ?o ?g. }
- W4317884041 endingPage "30" @default.
- W4317884041 startingPage "1" @default.
- W4317884041 abstract "Social network alignment, which aims to uncover the correspondence across different social networks, shows fundamental importance in a wide spectrum of applications such as cross-domain recommendation and information propagation. In the literature, the vast majority of the existing studies focus on the social network alignment at user level. In practice, the user-level alignment usually relies on abundant personal information and high-quality supervision, which is expensive and even impossible in the real-world scenario. Alternatively, we propose to study the problem of social group alignment across different social networks, focusing on the interests of social groups rather than personal information. However, social group alignment is non-trivial and faces significant challenges in both (i) feature inconsistency across different social networks and (ii) group discovery within a social network. To bridge this gap, we present a novel GroupAligner , a deep reinforcement learning with domain adaptation for social group alignment. In GroupAligner , to address the first issue, we propose the cycle domain adaptation approach with the Wasserstein distance to transfer the knowledge from the source social network, aligning the feature space of social networks in the distribution level. To address the second issue, we model the group discovery as a sequential decision process with reinforcement learning in which the policy is parameterized by a proposed p roximity-enhanced G raph N eural N etwork (pGNN) and a GNN-based discriminator to score the reward. Finally, we utilize pre-training and teacher forcing to stabilize the learning process of GroupAligner . Extensive experiments on several real-world datasets are conducted to evaluate GroupAligner , and experimental results show that GroupAligner outperforms the alternative methods for social group alignment." @default.
- W4317884041 created "2023-01-25" @default.
- W4317884041 creator A5000597313 @default.
- W4317884041 creator A5013328690 @default.
- W4317884041 creator A5015559474 @default.
- W4317884041 creator A5021236152 @default.
- W4317884041 creator A5033632697 @default.
- W4317884041 creator A5038754344 @default.
- W4317884041 creator A5051671090 @default.
- W4317884041 creator A5053580870 @default.
- W4317884041 creator A5078537850 @default.
- W4317884041 date "2023-05-22" @default.
- W4317884041 modified "2023-09-23" @default.
- W4317884041 title "<scp>GroupAligner</scp> : A Deep Reinforcement Learning with Domain Adaptation for Social Group Alignment" @default.
- W4317884041 cites W2127048411 @default.
- W4317884041 cites W2131681506 @default.
- W4317884041 cites W2139694940 @default.
- W4317884041 cites W2151936673 @default.
- W4317884041 cites W2207622687 @default.
- W4317884041 cites W2212315060 @default.
- W4317884041 cites W2547646153 @default.
- W4317884041 cites W2598689838 @default.
- W4317884041 cites W2621145626 @default.
- W4317884041 cites W2753758798 @default.
- W4317884041 cites W2767849480 @default.
- W4317884041 cites W2774854434 @default.
- W4317884041 cites W2786401568 @default.
- W4317884041 cites W2884596205 @default.
- W4317884041 cites W299101407 @default.
- W4317884041 cites W3001437801 @default.
- W4317884041 cites W3187845168 @default.
- W4317884041 cites W4210746245 @default.
- W4317884041 cites W4213170134 @default.
- W4317884041 doi "https://doi.org/10.1145/3580509" @default.
- W4317884041 hasPublicationYear "2023" @default.
- W4317884041 type Work @default.
- W4317884041 citedByCount "0" @default.
- W4317884041 crossrefType "journal-article" @default.
- W4317884041 hasAuthorship W4317884041A5000597313 @default.
- W4317884041 hasAuthorship W4317884041A5013328690 @default.
- W4317884041 hasAuthorship W4317884041A5015559474 @default.
- W4317884041 hasAuthorship W4317884041A5021236152 @default.
- W4317884041 hasAuthorship W4317884041A5033632697 @default.
- W4317884041 hasAuthorship W4317884041A5038754344 @default.
- W4317884041 hasAuthorship W4317884041A5051671090 @default.
- W4317884041 hasAuthorship W4317884041A5053580870 @default.
- W4317884041 hasAuthorship W4317884041A5078537850 @default.
- W4317884041 hasBestOaLocation W43178840411 @default.
- W4317884041 hasConcept C114614502 @default.
- W4317884041 hasConcept C114713312 @default.
- W4317884041 hasConcept C119857082 @default.
- W4317884041 hasConcept C134306372 @default.
- W4317884041 hasConcept C136764020 @default.
- W4317884041 hasConcept C138885662 @default.
- W4317884041 hasConcept C142189719 @default.
- W4317884041 hasConcept C150899416 @default.
- W4317884041 hasConcept C154945302 @default.
- W4317884041 hasConcept C2776401178 @default.
- W4317884041 hasConcept C33923547 @default.
- W4317884041 hasConcept C36503486 @default.
- W4317884041 hasConcept C41008148 @default.
- W4317884041 hasConcept C41895202 @default.
- W4317884041 hasConcept C4727928 @default.
- W4317884041 hasConcept C518677369 @default.
- W4317884041 hasConcept C97541855 @default.
- W4317884041 hasConceptScore W4317884041C114614502 @default.
- W4317884041 hasConceptScore W4317884041C114713312 @default.
- W4317884041 hasConceptScore W4317884041C119857082 @default.
- W4317884041 hasConceptScore W4317884041C134306372 @default.
- W4317884041 hasConceptScore W4317884041C136764020 @default.
- W4317884041 hasConceptScore W4317884041C138885662 @default.
- W4317884041 hasConceptScore W4317884041C142189719 @default.
- W4317884041 hasConceptScore W4317884041C150899416 @default.
- W4317884041 hasConceptScore W4317884041C154945302 @default.
- W4317884041 hasConceptScore W4317884041C2776401178 @default.
- W4317884041 hasConceptScore W4317884041C33923547 @default.
- W4317884041 hasConceptScore W4317884041C36503486 @default.
- W4317884041 hasConceptScore W4317884041C41008148 @default.
- W4317884041 hasConceptScore W4317884041C41895202 @default.
- W4317884041 hasConceptScore W4317884041C4727928 @default.
- W4317884041 hasConceptScore W4317884041C518677369 @default.
- W4317884041 hasConceptScore W4317884041C97541855 @default.
- W4317884041 hasFunder F4320321001 @default.
- W4317884041 hasFunder F4320335777 @default.
- W4317884041 hasFunder F4320335787 @default.
- W4317884041 hasIssue "3" @default.
- W4317884041 hasLocation W43178840411 @default.
- W4317884041 hasOpenAccess W4317884041 @default.
- W4317884041 hasPrimaryLocation W43178840411 @default.
- W4317884041 hasRelatedWork W2946016983 @default.
- W4317884041 hasRelatedWork W2960456850 @default.
- W4317884041 hasRelatedWork W3021430260 @default.
- W4317884041 hasRelatedWork W4221167745 @default.
- W4317884041 hasRelatedWork W4281645081 @default.
- W4317884041 hasRelatedWork W4308262314 @default.
- W4317884041 hasRelatedWork W4312200629 @default.
- W4317884041 hasRelatedWork W4319083788 @default.
- W4317884041 hasRelatedWork W4382286161 @default.