Advances of local low-rank collaborative filtering

[OstZ]

Local collaborative autoencoders Local latent space models for top-n recommendation Node-wise localization of graph neural networks Adaptive local low-rank matrix approximation for recommendation Learning low-rank representation for matrix completion Multi-component graph convolutional collaborative filtering Relational collaborative filtering: Modeling multiple item relations for recommendation Multi-level network embedding with boosted low-rank matrix approximation Mixture matrix approximation for collaborative filtering NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering GLIMG: Global and local item graphs for top-N recommender systems Fighting Mainstream Bias in Recommender Systems via Local Fine Tuning Local low-rank hawkes processes for temporal user-item interactions Constrained matrix factorization for course score prediction Collaborative filtering with user-item co-autoregressive models

noise Collaborative filtering with noisy ratings

ranking Utilization of efficient features, vectors and machine learning for ranking techniques Leveraging pointwise prediction with learning to rank for top-N recommendation Mix geographical information into local collaborative ranking for POI recommendation

[OstZ]

Local Low-Rank Matrix Approximation with Preference Selection of Anchor Points

• selects anchor-points using a heuristic method rather than randomly
• The basic idea is to generate candidate anchor-points by a clustering method, and then select respective anchor-points based on area density and anchor-points distance criteria.
• factorize rating matrix using PMF and obtain the user factor matrices U and item factor matrix V .

Adaptive Local Low-rank Matrix Approximation for Recommendation

• use Chinese Restaurant Process to dynamically allocate statistical capacity among clusters
• adaptively determine the rank of submatrix

Enhanced Low-Rank Matrix Approximation

• estimate low-rank matrices by formulating a convex optimization problem with nonconvex regularization.

Using Pre-trained model

• Interest-related item similarity model based on multimodal data for top-N recommendation
• Bilateral Self-unbiased Recommender Learning for Missing-not-at-Random Implicit Feedback
• Bilateral Self-unbiased Learning from Biased Implicit Feedback
• Synergizing Local and Global Models for Matrix Approximation
• Neural Collaborative Autoencoder
• Personalized deep reinforcement learning based recommendations
• A novel deep learning-based collaborative filtering model for recommendation system
• Utilization of efficient features, vectors and machine learning for ranking techniques
• Sequential Recommendation with Causal Behavior Discovery