ویراساینس.
مقاله‌ی دسترسی آزاد

A User-Interaction Parallel Networks Structure for Cold-Start Recommendation

['Yi Lin', '']

چکیده

Abstract The goal of the recommendation system is to recommend products users who may like it. collaborative filtering algorithm commonly used in systems needs collect explicit/implicit feedback data, and new do not leave behavioral data on product, which leads cold-start problem. This paper proposes a parallel network structure based user interaction, extracts features from interaction information, social media comment information forms matrix. graph neural introduced extract high-level embedded correlation role parallelism reduce computing cost further. Experiments standard sets prove that this method has certain degree improvement NDCG HR indicators compared baseline.

اسناد مشابه

  • Meta-Learned User Preference Estimator with Attention Network for Cold-Start Recommendation

    مقاله‌ی دسترسی آزاد۲۰۲۳Journal of physics['Shilong Liu', 'Yang Liu', 'Xiaotong Zhang', 'Chunjing Xu', 'Jie He', 'Yue Qi', '']

    Abstract One crucial challenge in the recommendation research field is cold-start problem. Meta-learning a feasible algorithm to reduce error of because it can adjust new tasks rapidly through relatively few updates. However, meta-learning does not take diverse interests users in

  • A Cold Start Recommendation System Using Item Correlation and User Similarity

    سند علمی۲۰۱۱Suchismit Mahapatra, Alwin Tareen, Ying Yang

    Conventional recommendation systems tend to focus on variations of well-known information retrieval techniques. We took a fresh approach, rather than to follow the traditional, commonly applied recommendation methodology of creating a user-item matrix, and then using them to make

  • SMINet: State-Aware Multi-Aspect Interests Representation Network for Cold-Start Users Recommendation

    مقاله‌ی دسترسی آزاد۲۰۲۲Proceedings of the ... AAAI Conference on Artificial Intelligence['Wanjie Tao', 'Yu You Li', 'Liangyue Li', 'Zulong Chen', 'Hong Wen', 'Peilin Chen', 'Tingting Liang', 'Quan Lu', '']

    Online travel platforms (OTPs), e.g., bookings.com and Ctrip.com, deliver experiences to online users by providing travel-related products. Although much progress has been made, the state-of-the-arts for cold-start problems are largely sub-optimal user representation, since they

  • Low-Rank Linear Cold-Start Recommendation from Social Data

    سند علمی۲۰۱۷AAAISuvash Sedhain, Aditya Krishna Menon, Scott Sanner, Lexing Xie

    The cold-start problem involves recommendation of content to new users of a system, for whom there is no historical preference information available. This proves a challenge for collaborative filtering algorithms that inherently rely on such information. Recent work has shown tha

  • Metadata Embeddings for User and Item Cold-start Recommendations

    سند علمی۲۰۱۵CBRecSys@RecSysMaciej Kula

    I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features’ latent factors. The model outperforms both collaborative and content-based models in cold-start or sparse interaction data scenarios (using both user and i

  • Transferring User Interests Across Websites with Unstructured Text for Cold-Start Recommendation

    سند علمی۲۰۱۶EMNLPYu-Yang Huang, Shou-De Lin

    In this work, we investigate the possibility of cross-website transfer learning for tackling the cold-start problem. To address the coldstart issues commonly present in a collaborative ltering (CF) system, most existing crossdomain CF models require auxiliary rating data from ano