Cargando…
PME: pruning-based multi-size embedding for recommender systems
Embedding is widely used in recommendation models to learn feature representations. However, the traditional embedding technique that assigns a fixed size to all categorical features may be suboptimal due to the following reasons. In recommendation domain, the majority of categorical features'...
Autores principales: | Liu, Zirui, Song, Qingquan, Li, Li, Choi, Soo-Hyun, Chen, Rui, Hu, Xia |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10311001/ https://www.ncbi.nlm.nih.gov/pubmed/37397622 http://dx.doi.org/10.3389/fdata.2023.1195742 |
Ejemplares similares
-
A survey on multi-objective recommender systems
por: Jannach, Dietmar, et al.
Publicado: (2023) -
Auto-GNN: Neural architecture search of graph neural networks
por: Zhou, Kaixiong, et al.
Publicado: (2022) -
Multi-list interfaces for recommender systems: survey and future directions
por: Loepp, Benedikt
Publicado: (2023) -
On Robustness of Neural Architecture Search Under Label Noise
por: Chen, Yi-Wei, et al.
Publicado: (2020) -
A World Full of Stereotypes? Further Investigation on Origin and Gender Bias in Multi-Lingual Word Embeddings
por: Kurpicz-Briki, Mascha, et al.
Publicado: (2021)