FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284704639> ?p ?o ?g. }

• W4284704639 abstract "Recommender systems aim to provide personalized services to users and are playing an increasingly important role in our daily lives. The key of recommender systems is to predict how likely users will interact with items based on their historical online behaviors, e.g., clicks, add-to-cart, purchases, etc. To exploit these user-item interactions, there are increasing efforts on considering the user-item interactions as a user-item bipartite graph and then performing information propagation in the graph via Graph Neural Networks (GNNs). Given the power of GNNs in graph representation learning, these GNNs-based recommendation methods have remarkably boosted the recommendation performance. Despite their success, most existing GNNs-based recommender systems overlook the existence of interactions caused by unreliable behaviors (e.g., random/bait clicks) and uniformly treat all the interactions, which can lead to sub-optimal and unstable performance. In this paper, we investigate the drawbacks (e.g., non-adaptive propagation and non-robustness) of existing GNN-based recommendation methods. To address these drawbacks, we introduce a principled graph trend collaborative filtering method and propose the Graph Trend Filtering Networks for recommendations (GTN) that can capture the adaptive reliability of the interactions. Comprehensive experiments and ablation studies are presented to verify and understand the effectiveness of the proposed framework. Our implementation based on PyTorch is available: https://github.com/wenqifan03/GTN-SIGIR2022." @default.
• W4284704639 created "2022-07-08" @default.
• W4284704639 creator A5011085153 @default.
• W4284704639 creator A5022892997 @default.
• W4284704639 creator A5040639891 @default.
• W4284704639 creator A5043696243 @default.
• W4284704639 creator A5053780153 @default.
• W4284704639 creator A5077970328 @default.
• W4284704639 date "2022-07-06" @default.
• W4284704639 modified "2023-10-17" @default.
• W4284704639 title "Graph Trend Filtering Networks for Recommendation" @default.
• W4284704639 cites W2039613841 @default.
• W4284704639 cites W2157881433 @default.
• W4284704639 cites W2253995343 @default.
• W4284704639 cites W2408728757 @default.
• W4284704639 cites W2740920897 @default.
• W4284704639 cites W2741249238 @default.
• W4284704639 cites W2788295351 @default.
• W4284704639 cites W2887092413 @default.
• W4284704639 cites W2914721378 @default.
• W4284704639 cites W2945623882 @default.
• W4284704639 cites W2963085847 @default.
• W4284704639 cites W2964938963 @default.
• W4284704639 cites W2972774416 @default.
• W4284704639 cites W2979068607 @default.
• W4284704639 cites W2996906638 @default.
• W4284704639 cites W3012955081 @default.
• W4284704639 cites W3014067266 @default.
• W4284704639 cites W3045200674 @default.
• W4284704639 cites W3081203761 @default.
• W4284704639 cites W3099936673 @default.
• W4284704639 cites W3100848837 @default.
• W4284704639 cites W3105279496 @default.
• W4284704639 cites W3114928288 @default.
• W4284704639 cites W3117655171 @default.
• W4284704639 cites W3155299750 @default.
• W4284704639 cites W3187174779 @default.
• W4284704639 cites W3208180646 @default.
• W4284704639 cites W4210257598 @default.
• W4284704639 cites W4284707459 @default.
• W4284704639 doi "https://doi.org/10.1145/3477495.3531985" @default.
• W4284704639 hasPublicationYear "2022" @default.
• W4284704639 type Work @default.
• W4284704639 citedByCount "20" @default.
• W4284704639 countsByYear W42847046392022 @default.
• W4284704639 countsByYear W42847046392023 @default.
• W4284704639 crossrefType "proceedings-article" @default.
• W4284704639 hasAuthorship W4284704639A5011085153 @default.
• W4284704639 hasAuthorship W4284704639A5022892997 @default.
• W4284704639 hasAuthorship W4284704639A5040639891 @default.
• W4284704639 hasAuthorship W4284704639A5043696243 @default.
• W4284704639 hasAuthorship W4284704639A5053780153 @default.
• W4284704639 hasAuthorship W4284704639A5077970328 @default.
• W4284704639 hasConcept C104317684 @default.
• W4284704639 hasConcept C119857082 @default.
• W4284704639 hasConcept C132525143 @default.
• W4284704639 hasConcept C154945302 @default.
• W4284704639 hasConcept C165696696 @default.
• W4284704639 hasConcept C185592680 @default.
• W4284704639 hasConcept C197657726 @default.
• W4284704639 hasConcept C21569690 @default.
• W4284704639 hasConcept C23123220 @default.
• W4284704639 hasConcept C38652104 @default.
• W4284704639 hasConcept C41008148 @default.
• W4284704639 hasConcept C55493867 @default.
• W4284704639 hasConcept C557471498 @default.
• W4284704639 hasConcept C59404180 @default.
• W4284704639 hasConcept C63479239 @default.
• W4284704639 hasConcept C80444323 @default.
• W4284704639 hasConceptScore W4284704639C104317684 @default.
• W4284704639 hasConceptScore W4284704639C119857082 @default.
• W4284704639 hasConceptScore W4284704639C132525143 @default.
• W4284704639 hasConceptScore W4284704639C154945302 @default.
• W4284704639 hasConceptScore W4284704639C165696696 @default.
• W4284704639 hasConceptScore W4284704639C185592680 @default.
• W4284704639 hasConceptScore W4284704639C197657726 @default.
• W4284704639 hasConceptScore W4284704639C21569690 @default.
• W4284704639 hasConceptScore W4284704639C23123220 @default.
• W4284704639 hasConceptScore W4284704639C38652104 @default.
• W4284704639 hasConceptScore W4284704639C41008148 @default.
• W4284704639 hasConceptScore W4284704639C55493867 @default.
• W4284704639 hasConceptScore W4284704639C557471498 @default.
• W4284704639 hasConceptScore W4284704639C59404180 @default.
• W4284704639 hasConceptScore W4284704639C63479239 @default.
• W4284704639 hasConceptScore W4284704639C80444323 @default.
• W4284704639 hasFunder F4320308008 @default.
• W4284704639 hasFunder F4320321001 @default.
• W4284704639 hasLocation W42847046391 @default.
• W4284704639 hasOpenAccess W4284704639 @default.
• W4284704639 hasPrimaryLocation W42847046391 @default.
• W4284704639 hasRelatedWork W1484355083 @default.
• W4284704639 hasRelatedWork W2041004656 @default.
• W4284704639 hasRelatedWork W2098758514 @default.
• W4284704639 hasRelatedWork W2103058005 @default.
• W4284704639 hasRelatedWork W2119611366 @default.
• W4284704639 hasRelatedWork W2170391450 @default.
• W4284704639 hasRelatedWork W2202724490 @default.
• W4284704639 hasRelatedWork W2735929803 @default.
• W4284704639 hasRelatedWork W3008845055 @default.
• W4284704639 hasRelatedWork W4220714703 @default.

• next