Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Parameter-Efficient Conversational Recommender System as a Language Processing Task (2024)
RA-Rec: An Efficient ID Representation Alignment Framework for LLM-based Recommendation (2024)
Rethinking Large Language Model Architectures for Sequential Recommendations (2024)
LGMRec: Local and Global Graph Learning for Multimodal Recommendation (2023)
User Embedding Model for Personalized Language Prompting (2024)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2024-02-20T01:21:40.122Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7376954555511475},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[{"reaction":"👍","users":["JaiSurya","vedalken","nachshonc","chiyuzhang"],"count":4}],"isReport":false}},{"id":"6664c55e4e36a92d1dd67cb9","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":176,"isUserFollowing":false},"createdAt":"2024-06-08T20:55:58.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"# Revolutionary Recommendation System: Meet SPAR with Long Engagement Attention! \n\nhttps://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/-87T9BKU0EVA92SGw_z8j.mp4 \n\n## Links 🔗:\n👉 Subscribe: https://www.youtube.com/@Arxflix\n👉 Twitter: https://x.com/arxflix\n👉 LMNT (Partner): https://lmnt.com/\n\n\nBy Arxflix\n![9t4iCUHx_400x400-1.jpg](https://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/v4S5zBurs0ouGNwYj1GEd.jpeg)","html":"

\n\t\n\t\t\n\t\n\t\n\t\tRevolutionary Recommendation System: Meet SPAR with Long Engagement Attention!\n\t\n

\n\n

\n\t\n\t\t\n\t\n\t\n\t\tLinks 🔗:\n\t\n

👉 Subscribe: https://www.youtube.com/@Arxflix
👉 Twitter: https://x.com/arxflix
👉 LMNT (Partner): https://lmnt.com/

By Arxflix
$\"9t4iCUHx_400x400-1.jpg\"$

\n","updatedAt":"2024-06-08T20:55:58.867Z","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":176,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5012816190719604},"editors":["blanchon"],"editorAvatarUrls":["/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2402.10555","authors":[{"_id":"65d2dc3dc6f238f8687cd62e","user":{"_id":"5fb2d92a9f63b546e74cb399","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1653523921526-5fb2d92a9f63b546e74cb399.png","isPro":false,"fullname":"chiyu_zhang","user":"chiyuzhang","type":"user"},"name":"Chiyu Zhang","status":"admin_assigned","statusLastChangedAt":"2024-02-19T15:28:27.272Z","hidden":false},{"_id":"65d2dc3dc6f238f8687cd62f","user":{"_id":"65d3810882939b6bb21a453f","avatarUrl":"/avatars/31041112c610e531bb0fbfb1f0c43257.svg","isPro":false,"fullname":"Yifei Sun","user":"sunyifei","type":"user"},"name":"Yifei Sun","status":"claimed_verified","statusLastChangedAt":"2024-02-19T17:05:24.217Z","hidden":false},{"_id":"65d2dc3dc6f238f8687cd630","user":{"_id":"62f94ec077b722f186641192","avatarUrl":"/avatars/37f4c7f2b6f59e2eac2d1b1b5cc88269.svg","isPro":false,"fullname":"jun chen","user":"junchen14","type":"user"},"name":"Jun Chen","status":"admin_assigned","statusLastChangedAt":"2024-02-19T15:30:13.784Z","hidden":false},{"_id":"65d2dc3dc6f238f8687cd631","user":{"_id":"64e7be5c0c47bf287ca5baf5","avatarUrl":"/avatars/a82dec23bde346f1479049f74e55004b.svg","isPro":false,"fullname":"Jie Lei","user":"jielei","type":"user"},"name":"Jie Lei","status":"admin_assigned","statusLastChangedAt":"2024-02-19T15:30:21.278Z","hidden":false},{"_id":"65d2dc3dc6f238f8687cd632","user":{"_id":"5feeae8dd8e0b2d24ed258cc","avatarUrl":"/avatars/1d66840db4ed6dc12bdee7ba8168ea9f.svg","isPro":false,"fullname":"Muhammad Abdul-Mageed","user":"mageed","type":"user"},"name":"Muhammad Abdul-Mageed","status":"admin_assigned","statusLastChangedAt":"2024-02-19T15:30:37.096Z","hidden":false},{"_id":"65d2dc3dc6f238f8687cd633","user":{"_id":"65b483c5ed110eb9f1ee62df","avatarUrl":"/avatars/29100098f5aed1735675d06c516a85b7.svg","isPro":false,"fullname":"Theron S. Wang","user":"TheronWong","type":"user"},"name":"Sinong Wang","status":"admin_assigned","statusLastChangedAt":"2024-02-19T15:30:43.635Z","hidden":true},{"_id":"65d2dc3dc6f238f8687cd634","name":"Rong Jin","hidden":false},{"_id":"65d2dc3dc6f238f8687cd635","name":"Sem Park","hidden":false},{"_id":"65d2dc3dc6f238f8687cd636","name":"Ning Yao","hidden":false},{"_id":"65d2dc3dc6f238f8687cd637","name":"Bo Long","hidden":false}],"publishedAt":"2024-02-16T10:36:38.000Z","submittedOnDailyAt":"2024-02-19T02:12:37.695Z","title":"SPAR: Personalized Content-Based Recommendation via Long Engagement\n Attention","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"Leveraging users' long engagement histories is essential for personalized\ncontent recommendations. The success of pretrained language models (PLMs) in\nNLP has led to their use in encoding user histories and candidate items,\nframing content recommendations as textual semantic matching tasks. However,\nexisting works still struggle with processing very long user historical text\nand insufficient user-item interaction. In this paper, we introduce a\ncontent-based recommendation framework, SPAR, which effectively tackles the\nchallenges of holistic user interest extraction from the long user engagement\nhistory. It achieves so by leveraging PLM, poly-attention layers and attention\nsparsity mechanisms to encode user's history in a session-based manner. The\nuser and item side features are sufficiently fused for engagement prediction\nwhile maintaining standalone representations for both sides, which is efficient\nfor practical model deployment. Moreover, we enhance user profiling by\nexploiting large language model (LLM) to extract global interests from user\nengagement history. Extensive experiments on two benchmark datasets demonstrate\nthat our framework outperforms existing state-of-the-art (SoTA) methods.","upvotes":35,"discussionId":"65d2dc3dc6f238f8687cd64e","githubRepo":"https://github.com/jyonn/legommenders","githubRepoAddedBy":"auto","ai_summary":"The SPAR framework enhances content recommendations by using pretrained language models, poly-attention layers, and large language models to effectively process long user engagement histories and predict user-item interactions.","ai_keywords":["pretrained language models","poly-attention layers","attention sparsity mechanisms","large language models"],"githubStars":30},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"62885a9182e8b16fb143ba16","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1653103235388-noauth.jpeg","isPro":false,"fullname":"Jun Naito","user":"njun","type":"user"},{"_id":"6538119803519fddb4a17e10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6538119803519fddb4a17e10/ffJMkdx-rM7VvLTCM6ri_.jpeg","isPro":false,"fullname":"samusenps","user":"samusenps","type":"user"},{"_id":"65d3c56682939b6bb2303c27","avatarUrl":"/avatars/89c5351dcc43c4b2f9ab47e6969afa45.svg","isPro":false,"fullname":"Amit siwal","user":"siwal","type":"user"},{"_id":"61a9e0d0629526edf57094f3","avatarUrl":"/avatars/77ccc569d50ef68d4bf663623993a200.svg","isPro":false,"fullname":"Agis Oikonomou","user":"agipof","type":"user"},{"_id":"64dabbb0aeec6bc7c8a92bea","avatarUrl":"/avatars/ff729cba034da9d4911cfe02fa8f321c.svg","isPro":false,"fullname":"Joseph C Steward","user":"jsteward2930","type":"user"},{"_id":"5feeae8dd8e0b2d24ed258cc","avatarUrl":"/avatars/1d66840db4ed6dc12bdee7ba8168ea9f.svg","isPro":false,"fullname":"Muhammad Abdul-Mageed","user":"mageed","type":"user"},{"_id":"641aa07e91e3376a057b95b6","avatarUrl":"/avatars/1c33146dd10b88ba594ef610c8137672.svg","isPro":false,"fullname":"Yihang He","user":"clicktoedit233","type":"user"},{"_id":"5fb2d92a9f63b546e74cb399","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1653523921526-5fb2d92a9f63b546e74cb399.png","isPro":false,"fullname":"chiyu_zhang","user":"chiyuzhang","type":"user"},{"_id":"62fd83d2cad078c7973099a9","avatarUrl":"/avatars/62e9e4e53a42945c51b1296955f5d760.svg","isPro":true,"fullname":"Md Tawkat Islam Khondaker","user":"Tawkat","type":"user"},{"_id":"65c55330e286dbda4e81c9a6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65c55330e286dbda4e81c9a6/1goq_45j5AVWjxfNavBgk.jpeg","isPro":false,"fullname":"Wei Rui Chen","user":"wrchen1","type":"user"},{"_id":"644040d77841867cd5b4d670","avatarUrl":"/avatars/0fc982cc2e2baaaf673f1871de51520a.svg","isPro":false,"fullname":"Peter Sullivan","user":"prsull","type":"user"},{"_id":"630fc966dd31b2a8dbe6699e","avatarUrl":"/avatars/f9d1d2ffaf347dc6c848037a001dd1ae.svg","isPro":false,"fullname":"Alcides Alcoba Inciarte","user":"Al-Alcoba-Inciarte","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":3}">

Papers

arxiv:2402.10555

SPAR: Personalized Content-Based Recommendation via Long Engagement Attention

Published on Feb 16, 2024

· Submitted by

AK on Feb 19, 2024

#3 Paper of the day

Upvote

Authors:

Chiyu Zhang ,

Yifei Sun ,

Jun Chen ,

Jie Lei ,

Muhammad Abdul-Mageed ,

Sinong Wang ,

Abstract

The SPAR framework enhances content recommendations by using pretrained language models, poly-attention layers, and large language models to effectively process long user engagement histories and predict user-item interactions.

AI-generated summary

Leveraging users' long engagement histories is essential for personalized content recommendations. The success of pretrained language models (PLMs) in NLP has led to their use in encoding user histories and candidate items, framing content recommendations as textual semantic matching tasks. However, existing works still struggle with processing very long user historical text and insufficient user-item interaction. In this paper, we introduce a content-based recommendation framework, SPAR, which effectively tackles the challenges of holistic user interest extraction from the long user engagement history. It achieves so by leveraging PLM, poly-attention layers and attention sparsity mechanisms to encode user's history in a session-based manner. The user and item side features are sufficiently fused for engagement prediction while maintaining standalone representations for both sides, which is efficient for practical model deployment. Moreover, we enhance user profiling by exploiting large language model (LLM) to extract global interests from user engagement history. Extensive experiments on two benchmark datasets demonstrate that our framework outperforms existing state-of-the-art (SoTA) methods.

View arXiv page View PDF GitHub 30 auto Add to collection