Privileged Graph Distillation for Cold Start Recommendation

  title={Privileged Graph Distillation for Cold Start Recommendation},
  author={Shuai Wang and Kun Zhang and Le Wu and Haiping Ma and Richang Hong and Meng Wang},
  journal={Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  • Shuai Wang, Kun Zhang, +3 authors Meng Wang
  • Published 2021
  • Computer Science
  • Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
The cold start problem in recommender systems is a long-standing challenge, which requires recommending to new users (items) based on attributes without any historical interaction records. In these recommendation systems, warm users (items) have privileged collaborative signals of interaction records compared to cold start users (items), and these Collaborative Filtering (CF) signals are shown to have competing performance for recommendation. Many researchers proposed to learn the correlation… Expand

Figures and Tables from this paper


Recommendation for New Users and New Items via Randomized Training and Mixture-of-Experts Transformation
A novel model designed to overcome the error superimposition issue and improve model quality is proposed, and extensive experiments show the effectiveness of the proposed model over state-of-the-art alternatives. Expand
Learning Attribute-to-Feature Mappings for Cold-Start Recommendations
This work uses the mapping concept to construct an attribute-aware matrix factorization model for item recommendation from implicit, positive-only feedback, and shows that this approach provides good predictive accuracy, while the prediction time only grows by a constant factor. Expand
Functional matrix factorizations for cold-start recommendation
Functional matrix factorization is presented, a novel cold-start recommendation method that solves the problem of initial interview construction within the context of learning user and item profiles and associate latent profiles for each node of the tree, which allows the profiles to be gradually refined through the interview process based on user responses. Expand
Neural Graph Collaborative Filtering
This work develops a new recommendation framework Neural Graph Collaborative Filtering (NGCF), which exploits the user-item graph structure by propagating embeddings on it, effectively injecting the collaborative signal into the embedding process in an explicit manner. Expand
Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation
This paper proposes an inductive Graph based Transfer learning framework for personalized video highlight Recommendation (TransGRec), which is composed of a graph neural network followed by an item embedding transfer network that exploits the higher-order proximity between users and segments to alleviate the user cold-start problem. Expand
Social collaborative filtering for cold-start recommendations
This work formalizes neighborhood-based methods for cold-start collaborative filtering in a generalized matrix algebra framework that does not require purchase data for target users when their side information is available. Expand
A Neural Influence Diffusion Model for Social Recommendation
A deep influence propagation model is proposed to stimulate how users are influenced by the recursive social diffusion process for social recommendation, with more than 13% performance improvements over the best baselines for top-10 recommendation on the two datasets. Expand
Collaborative Deep Learning for Recommender Systems
A hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix is proposed, which can significantly advance the state of the art. Expand
Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System
  • Jiaxi Tang, Ke Wang
  • Computer Science, Mathematics
  • KDD
  • 2018
A novel way to train ranking models, such as recommender systems, that are both effective and efficient is proposed, and a smaller student model is trained to learn to rank documents/items from both the training data and the supervision of a larger teacher model. Expand
DropoutNet: Addressing Cold Start in Recommender Systems
This work proposes a neural network based latent model called DropoutNet to address the cold start problem in recommender systems and shows that neural network models can be explicitly trained for cold start through dropout. Expand