interest exploration

DataFunSummit

Jan 15, 2025 · Artificial Intelligence

Decentralized Distribution in Xiaohongshu: Strengthening Sideinfo, Multimodal Fusion, and Interest Exploration

This article details Xiaohongshu's technical approaches to solving decentralized content distribution by enhancing side‑information usage, integrating multimodal signals across the recommendation pipeline, applying graph‑based models, and implementing interest exploration and protection mechanisms, while also outlining future research directions.

Large ModelsRecommendation systemsdecentralized distribution

0 likes · 24 min read

Decentralized Distribution in Xiaohongshu: Strengthening Sideinfo, Multimodal Fusion, and Interest Exploration

DataFunSummit

Oct 29, 2024 · Artificial Intelligence

Decentralized Distribution in Xiaohongshu: Strengthening Sideinfo, Multimodal Fusion, and Interest Exploration

This article details Xiaohongshu's technical approaches to decentralized content distribution, covering business background, core challenges, high‑frequency recommendation pipelines, link‑level analysis, sideinfo decoupling, graph‑model integration, multimodal signal fusion, explicit interest exploration, interest protection, and future research directions.

Recommendation systemsdecentralized distributiongraph models

0 likes · 24 min read

DataFunTalk

Jul 31, 2024 · Artificial Intelligence

Decentralized Distribution in Xiaohongshu Recommendation System: Sideinfo, Multi‑modal Fusion, Interest Exploration and Future Directions

This article presents Xiaohongshu's technical solutions for decentralized content distribution, covering the definition of the problem, fast and accurate learning, side‑information modeling, graph‑based multi‑modal fusion, interest exploration and protection, and future research directions such as generative recommendation and large‑model driven user profiling.

Large Modelsdecentralized distributioninterest exploration

0 likes · 25 min read

Decentralized Distribution in Xiaohongshu Recommendation System: Sideinfo, Multi‑modal Fusion, Interest Exploration and Future Directions