Sequence-to-sequence Recommendation

Sequence-to-Sequence Recommendation is a sequence modeling framework that generates personalized recommendations by mapping an input sequence of user-item interactions to an output sequence of future items through an encoder-decoder architecture, distinguishing it from pointwise or session-based methods by explicitly modeling sequential dependencies in both input and output.

129

Publications

9.8K

Citations

524

Authors

157

Institutions

Publications per year

2017–2026

121

Authors

524

  1. GX
    Guandong Xu

    University of Technology Sydney, Australia

    5 publications · 287 citations

    5

    h-index

  2. TC
    Tat‐Seng Chua

    National University of Singapore, Singapore

    5 publications · 177 citations

    5

    h-index

  3. DW
    Dongjing Wang

    Hangzhou Dianzi University, China

    4 publications · 225 citations

    4

    h-index

  4. SW
    Shu Wu

    Chinese Academy of Sciences, China

    4 publications · 283 citations

    4

    h-index

  5. LW
    Liang Wang

    Chinese Academy of Sciences, China

    4 publications · 283 citations

    4

    h-index

1–5 of 524

Venues

  1. arXiv (Cornell University)

    Repository · 10 publications · 463 citations

    10

    h-index

  2. Expert Systems with Applications

    5 publications · 114 citations

    5

    h-index

  3. Information Processing & Management

    5 publications · 144 citations

    5

    h-index

  4. Frontiers of Computer Science

    4 publications · 94 citations

    4

    h-index

  5. Knowledge-Based Systems

    3 publications · 73 citations

    3

    h-index

1–5