Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286564606> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4286564606 endingPage "109349" @default.
- W4286564606 startingPage "109349" @default.
- W4286564606 abstract "The key problem of sequential recommendation is how to capture user sequential patterns and enrich user sequential representations from historical interactions, mainly due to the uncertainty of user behavior and the limited information. The RNN-based methods capture the long- and short-term level patterns. The CNN-based methods treat the representation of the user’s historical interaction as an “image”, and discover the point-level patterns, union-level patterns and union-level with skip once. The attention-based methods mine the focus-level patterns. However, all the previous methods have only studied how to capture users’ sequential patterns in the time domain. In many cases, if we only consider the time domain information, these methods will have trouble in mining the user’s sequential patterns. To solve this problem, we consider the frequency domain to capture frequency-level patterns for the first time. Because a non-periodic historical behavior sequence in the time domain may be brutal to reflect the user’s intention but much more accessible in the frequency domain. In light of this, we propose a novel Attention-based Frequency-aware Multi-scale Network (AFMN) for Sequential Recommendation. We introduce Fourier transform to decompose the simple embedding vector, the representation of the user’s historical interaction, into a multi-frequency embedding vector to enrich the user’s behavior sequence representation. The frequency-aware attention layers adaptively focus on the important frequency components and output a refined multi-frequency embedding vector. Given the multi-frequency embedding vector, we develop a non-local attention module to aggregate attribute-level and item-level features of the previous L items. Empirical results on four public benchmark datasets show that our method can achieve a significant improvement over the state-of-the-art baselines." @default.
- W4286564606 created "2022-07-22" @default.
- W4286564606 creator A5054472031 @default.
- W4286564606 creator A5056646905 @default.
- W4286564606 creator A5072710254 @default.
- W4286564606 creator A5078699661 @default.
- W4286564606 date "2022-09-01" @default.
- W4286564606 modified "2023-10-02" @default.
- W4286564606 title "Attention-based Frequency-aware Multi-scale Network for Sequential Recommendation" @default.
- W4286564606 cites W2054141820 @default.
- W4286564606 cites W2057763140 @default.
- W4286564606 cites W2082484042 @default.
- W4286564606 cites W2142144955 @default.
- W4286564606 cites W2963420686 @default.
- W4286564606 cites W2965857254 @default.
- W4286564606 cites W2972724570 @default.
- W4286564606 cites W2973224900 @default.
- W4286564606 cites W3038083583 @default.
- W4286564606 cites W3097021616 @default.
- W4286564606 doi "https://doi.org/10.1016/j.asoc.2022.109349" @default.
- W4286564606 hasPublicationYear "2022" @default.
- W4286564606 type Work @default.
- W4286564606 citedByCount "5" @default.
- W4286564606 countsByYear W42865646062023 @default.
- W4286564606 crossrefType "journal-article" @default.
- W4286564606 hasAuthorship W4286564606A5054472031 @default.
- W4286564606 hasAuthorship W4286564606A5056646905 @default.
- W4286564606 hasAuthorship W4286564606A5072710254 @default.
- W4286564606 hasAuthorship W4286564606A5078699661 @default.
- W4286564606 hasConcept C119857082 @default.
- W4286564606 hasConcept C120665830 @default.
- W4286564606 hasConcept C121332964 @default.
- W4286564606 hasConcept C124101348 @default.
- W4286564606 hasConcept C134306372 @default.
- W4286564606 hasConcept C153180895 @default.
- W4286564606 hasConcept C154945302 @default.
- W4286564606 hasConcept C17744445 @default.
- W4286564606 hasConcept C19118579 @default.
- W4286564606 hasConcept C192209626 @default.
- W4286564606 hasConcept C199539241 @default.
- W4286564606 hasConcept C26517878 @default.
- W4286564606 hasConcept C2776359362 @default.
- W4286564606 hasConcept C2778112365 @default.
- W4286564606 hasConcept C31972630 @default.
- W4286564606 hasConcept C33923547 @default.
- W4286564606 hasConcept C36503486 @default.
- W4286564606 hasConcept C38652104 @default.
- W4286564606 hasConcept C41008148 @default.
- W4286564606 hasConcept C41608201 @default.
- W4286564606 hasConcept C54355233 @default.
- W4286564606 hasConcept C86803240 @default.
- W4286564606 hasConcept C94625758 @default.
- W4286564606 hasConceptScore W4286564606C119857082 @default.
- W4286564606 hasConceptScore W4286564606C120665830 @default.
- W4286564606 hasConceptScore W4286564606C121332964 @default.
- W4286564606 hasConceptScore W4286564606C124101348 @default.
- W4286564606 hasConceptScore W4286564606C134306372 @default.
- W4286564606 hasConceptScore W4286564606C153180895 @default.
- W4286564606 hasConceptScore W4286564606C154945302 @default.
- W4286564606 hasConceptScore W4286564606C17744445 @default.
- W4286564606 hasConceptScore W4286564606C19118579 @default.
- W4286564606 hasConceptScore W4286564606C192209626 @default.
- W4286564606 hasConceptScore W4286564606C199539241 @default.
- W4286564606 hasConceptScore W4286564606C26517878 @default.
- W4286564606 hasConceptScore W4286564606C2776359362 @default.
- W4286564606 hasConceptScore W4286564606C2778112365 @default.
- W4286564606 hasConceptScore W4286564606C31972630 @default.
- W4286564606 hasConceptScore W4286564606C33923547 @default.
- W4286564606 hasConceptScore W4286564606C36503486 @default.
- W4286564606 hasConceptScore W4286564606C38652104 @default.
- W4286564606 hasConceptScore W4286564606C41008148 @default.
- W4286564606 hasConceptScore W4286564606C41608201 @default.
- W4286564606 hasConceptScore W4286564606C54355233 @default.
- W4286564606 hasConceptScore W4286564606C86803240 @default.
- W4286564606 hasConceptScore W4286564606C94625758 @default.
- W4286564606 hasLocation W42865646061 @default.
- W4286564606 hasOpenAccess W4286564606 @default.
- W4286564606 hasPrimaryLocation W42865646061 @default.
- W4286564606 hasRelatedWork W2329452785 @default.
- W4286564606 hasRelatedWork W2356380379 @default.
- W4286564606 hasRelatedWork W2961085424 @default.
- W4286564606 hasRelatedWork W3046775127 @default.
- W4286564606 hasRelatedWork W4285260836 @default.
- W4286564606 hasRelatedWork W4286629047 @default.
- W4286564606 hasRelatedWork W4306321456 @default.
- W4286564606 hasRelatedWork W4306674287 @default.
- W4286564606 hasRelatedWork W84951255 @default.
- W4286564606 hasRelatedWork W4224009465 @default.
- W4286564606 hasVolume "127" @default.
- W4286564606 isParatext "false" @default.
- W4286564606 isRetracted "false" @default.
- W4286564606 workType "article" @default.