Recommendation Systems
1457 papers with code • 54 benchmarks • 54 datasets
The Recommendation Systems task is to produce a list of recommendations for a user. The most common methods used in recommender systems are factor models (Koren et al., 2009; Weimer et al., 2007; Hidasi & Tikk, 2012) and neighborhood methods (Sarwar et al., 2001; Koren, 2008). Factor models work by decomposing the sparse user-item interactions matrix to a set of d dimensional vectors one for each item and user in the dataset. Factor models are hard to apply in session-based recommendations due to the absence of a user profile. On the other hand, neighborhood methods, which rely on computing similarities between items (or users) are based on co-occurrences of items in sessions (or user profiles). Neighborhood methods have been used extensively in session-based recommendations.
( Image credit: CuMF_SGD )
Benchmarks
These leaderboards are used to track progress in Recommendation Systems
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Recommendation Systems models and implementations
MovieLens
Netflix Prize
Gowalla
MIND
Yelp2018
ReDial
Polyvore
Subtasks
Latest papers with no code
Graph Machine Learning in the Era of Large Language Models (LLMs)
Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability.
Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It
There has been a growing interest in off-policy evaluation in the literature such as recommender systems and personalized medicine.
Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems
The recommendation with a cache is a solution to this problem, where a user-wise result cache is used to provide recommendations when the recommender system cannot afford a real-time computation.
General Item Representation Learning for Cold-start Content Recommendations
Cold-start item recommendation is a long-standing challenge in recommendation systems.
Multi-channel Emotion Analysis for Consensus Reaching in Group Movie Recommendation Systems
It can be challenging to choose a movie that appeals to the emotions of a diverse group.
Beyond Collaborative Filtering: A Relook at Task Formulation in Recommender Systems
That is, we often conceptualize RecSys as the task of predicting missing values in a static user-item interaction matrix, rather than predicting a user's decision on the next interaction within a dynamic, changing, and application-specific context.
MARec: Metadata Alignment for cold-start Recommendation
For many recommender systems the primary data source is a historical record of user clicks.
An Off-Policy Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems
Recently, to optimize long-term user satisfaction within a recommendation session, Reinforcement Learning (RL) is used for MTF in the industry.
Relationship Discovery for Drug Recommendation
Medication recommendation systems are designed to deliver personalized drug suggestions that are closely aligned with individual patient needs.
How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective
Our comprehensive theoretical and empirical investigations lead to two core insights: 1) Item popularity is memorized in the principal singular vector of the score matrix predicted by the recommendation model; 2) The dimension collapse phenomenon amplifies the impact of principal singular vector on model predictions, intensifying the popularity bias.
