Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387579692> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4387579692 endingPage "122060" @default.
- W4387579692 startingPage "122060" @default.
- W4387579692 abstract "Recent Transformer-based architectures have achieved encouraging performance for sequential recommendation, whereas their computational complexity is quadratic to the sequence length. MLP4Rec is a promising solution to settle this issue, which captures item transition patterns by a MLP-Mixer layer. Despite effectiveness, we argue that it still faces two critical limitations. On the one hand, it employs the one-hot ID technique to generate each user/item embedding, which has no specific semantics apart from being an identifier. In this case, given these ID embeddings as the original input of a MLP-Mixer layer, it is non-trivial to distill the useful information for other layers. On the other hand, it fails to explicitly differentiate the significance of different factors of an item, which is unrealistic to capture the user’s true taste in a short context; meanwhile, it also does not discriminate the importance of each item instance given the recent actions of a user. To overcome such two limitations, we propose a new solution for sequential recommendation, namely a graph Gating-Mixer Recommender (GMRec). Our solution decomposes the sequential recommendation workflow into three steps. First, by means of graph neural networks, we embed a linear graph propagation module to produce high-quality user and item embeddings. Afterwards, we replace the MLP-Mixer layer in MLP4Rec with a devised dual gating block, which could dynamically control what features and which items can be passed to the downstream layers. Lastly, we devise a user-specific gating strategy to adaptively integrate two components in GMRec. Extensive experiments are performed on the Beauty, Cellphone, Gowalla, and ML-10M datasets, demonstrating the rationality and effectiveness of our solution. Specifically, when Precision@10, Recall@10, MAP@10, and NDCG@10 are adopted as evaluation metrics, the performance gains of GMRec over recent state-of-the-art methods on four datasets are 11.91%, 19.46%, 9.56%, and 13.01%, respectively. Our implemented codes and datatsets are available via https://github.com/wubinzzu/GMRec." @default.
- W4387579692 created "2023-10-13" @default.
- W4387579692 creator A5005167596 @default.
- W4387579692 creator A5009747669 @default.
- W4387579692 creator A5021442995 @default.
- W4387579692 creator A5044221728 @default.
- W4387579692 creator A5045940041 @default.
- W4387579692 creator A5047807693 @default.
- W4387579692 date "2023-10-01" @default.
- W4387579692 modified "2023-10-14" @default.
- W4387579692 title "Graph gating-mixer for sequential recommendation" @default.
- W4387579692 cites W2980733333 @default.
- W4387579692 cites W2980778868 @default.
- W4387579692 cites W3021893476 @default.
- W4387579692 cites W3097300053 @default.
- W4387579692 cites W3105472188 @default.
- W4387579692 cites W4210264905 @default.
- W4387579692 cites W4213217984 @default.
- W4387579692 cites W4224230118 @default.
- W4387579692 cites W4225160227 @default.
- W4387579692 cites W4290648792 @default.
- W4387579692 cites W4306955484 @default.
- W4387579692 cites W4310333559 @default.
- W4387579692 cites W4319302606 @default.
- W4387579692 cites W4320713304 @default.
- W4387579692 cites W4327919513 @default.
- W4387579692 cites W4328099349 @default.
- W4387579692 cites W4379931881 @default.
- W4387579692 doi "https://doi.org/10.1016/j.eswa.2023.122060" @default.
- W4387579692 hasPublicationYear "2023" @default.
- W4387579692 type Work @default.
- W4387579692 citedByCount "0" @default.
- W4387579692 crossrefType "journal-article" @default.
- W4387579692 hasAuthorship W4387579692A5005167596 @default.
- W4387579692 hasAuthorship W4387579692A5009747669 @default.
- W4387579692 hasAuthorship W4387579692A5021442995 @default.
- W4387579692 hasAuthorship W4387579692A5044221728 @default.
- W4387579692 hasAuthorship W4387579692A5045940041 @default.
- W4387579692 hasAuthorship W4387579692A5047807693 @default.
- W4387579692 hasConcept C132525143 @default.
- W4387579692 hasConcept C154504017 @default.
- W4387579692 hasConcept C154945302 @default.
- W4387579692 hasConcept C199360897 @default.
- W4387579692 hasConcept C23123220 @default.
- W4387579692 hasConcept C41008148 @default.
- W4387579692 hasConcept C41608201 @default.
- W4387579692 hasConcept C557471498 @default.
- W4387579692 hasConcept C80444323 @default.
- W4387579692 hasConceptScore W4387579692C132525143 @default.
- W4387579692 hasConceptScore W4387579692C154504017 @default.
- W4387579692 hasConceptScore W4387579692C154945302 @default.
- W4387579692 hasConceptScore W4387579692C199360897 @default.
- W4387579692 hasConceptScore W4387579692C23123220 @default.
- W4387579692 hasConceptScore W4387579692C41008148 @default.
- W4387579692 hasConceptScore W4387579692C41608201 @default.
- W4387579692 hasConceptScore W4387579692C557471498 @default.
- W4387579692 hasConceptScore W4387579692C80444323 @default.
- W4387579692 hasLocation W43875796921 @default.
- W4387579692 hasOpenAccess W4387579692 @default.
- W4387579692 hasPrimaryLocation W43875796921 @default.
- W4387579692 hasRelatedWork W1979633005 @default.
- W4387579692 hasRelatedWork W2150182025 @default.
- W4387579692 hasRelatedWork W2418190244 @default.
- W4387579692 hasRelatedWork W2932872266 @default.
- W4387579692 hasRelatedWork W3092950680 @default.
- W4387579692 hasRelatedWork W3197542405 @default.
- W4387579692 hasRelatedWork W4246980185 @default.
- W4387579692 hasRelatedWork W4317039510 @default.
- W4387579692 hasRelatedWork W4378651134 @default.
- W4387579692 hasRelatedWork W4386781444 @default.
- W4387579692 isParatext "false" @default.
- W4387579692 isRetracted "false" @default.
- W4387579692 workType "article" @default.