MARS: Matching Attribute-aware Representations for Text-based Sequential Recommendation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912014126809088 |
|---|---|
| author | Kim, Hyunsoo Kim, Junyoung Choi, Minjin Lee, Sunkyung Lee, Jongwuk |
| author_facet | Kim, Hyunsoo Kim, Junyoung Choi, Minjin Lee, Sunkyung Lee, Jongwuk |
| contents | Sequential recommendation aims to predict the next item a user is likely to prefer based on their sequential interaction history. Recently, text-based sequential recommendation has emerged as a promising paradigm that uses pre-trained language models to exploit textual item features to enhance performance and facilitate knowledge transfer to unseen datasets. However, existing text-based recommender models still struggle with two key challenges: (i) representing users and items with multiple attributes, and (ii) matching items with complex user interests. To address these challenges, we propose a novel model, Matching Attribute-aware Representations for Text-based Sequential Recommendation (MARS). MARS extracts detailed user and item representations through attribute-aware text encoding, capturing diverse user intents with multiple attribute-aware representations. It then computes user-item scores via attribute-wise interaction matching, effectively capturing attribute-level user preferences. Our extensive experiments demonstrate that MARS significantly outperforms existing sequential models, achieving improvements of up to 24.43% and 29.26% in Recall@10 and NDCG@10 across five benchmark datasets. Code is available at https://github.com/junieberry/MARS |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00702 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MARS: Matching Attribute-aware Representations for Text-based Sequential Recommendation Kim, Hyunsoo Kim, Junyoung Choi, Minjin Lee, Sunkyung Lee, Jongwuk Information Retrieval Sequential recommendation aims to predict the next item a user is likely to prefer based on their sequential interaction history. Recently, text-based sequential recommendation has emerged as a promising paradigm that uses pre-trained language models to exploit textual item features to enhance performance and facilitate knowledge transfer to unseen datasets. However, existing text-based recommender models still struggle with two key challenges: (i) representing users and items with multiple attributes, and (ii) matching items with complex user interests. To address these challenges, we propose a novel model, Matching Attribute-aware Representations for Text-based Sequential Recommendation (MARS). MARS extracts detailed user and item representations through attribute-aware text encoding, capturing diverse user intents with multiple attribute-aware representations. It then computes user-item scores via attribute-wise interaction matching, effectively capturing attribute-level user preferences. Our extensive experiments demonstrate that MARS significantly outperforms existing sequential models, achieving improvements of up to 24.43% and 29.26% in Recall@10 and NDCG@10 across five benchmark datasets. Code is available at https://github.com/junieberry/MARS |
| title | MARS: Matching Attribute-aware Representations for Text-based Sequential Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2409.00702 |