추천 시스템 관련된 논문들은 정말 많은데 이 분야를 처음 접한 사람이라면 어떤걸 먼저 봐야할지 감이 잡히지 않는다.
또한 추천 시스템 아래에 수많은 하위 영역이 있는데 그 분야에서 어떤게 좋은 논문인지 모를 때가 있다.
이럴 때는 이 링크를 보면 많은 도움이 된다.
튜토리얼과 서베이 논문 부터 시작해서 소셜, 딥러닝, 콜드 스타트, POI, CTR, KG 등 다양한 세부 주제를 다룰뿐만 아니라 요즘 핫한 LLM을 이용한 논문과 Pinterest의 PinSAGE 등과 같은 기업체의 논문까지 소개하고 있다. 세부 분야에 대한 설명은 아래와 같다.
00-Tutorials:
contain so many tutorials on recommendation systems given by prominent researchers at many top-tier conferences
01-Surveys:
a set of comprehensive surveys about recommender system, such as hybrid recommender systems, social recommender systems, poi recommender systems, deep-learning based recommonder systems and so on.
02-General RS:
a set of famous recommendation papers which make predictions with some classic models and practical theory.
03-Social RS:
several papers which utilize trust/social information in order to alleviate the sparsity of ratings data.
04-Deep Learning-based RS:
a set of papers to build a recommender system with deep learning techniques.
05-Cold Start Problem in RS:
some papers specifically dealing with the cold start problems inherent in collaborative filtering.
06-POI RS:
it focus on helping users explore attractive locations with the information of location-based social networks.
07-Efficient RS:
some techniques for efficient recommender system in order to training and making recommendation efficiently.
08-EE Problem in RS:
some articles about exploration and exploitation problems in recommendation.
09-Explainability on RS:
it focus on addressing the problem of 'why', they not only provide the user with the recommendations, but also make the user aware why such items are recommended by generating recommendation explanations.
10-CTR Prediction for RS:
as one part of recommendation, click-through rate prediction focuses on the elaboration of candidate sets for recommendation.
11-Knowledge Graph for RS:
knowledge graph, as the side information of behavior interaction matrix in recent years, which can effectively alleviate the problem of data sparsity and cold start, and can provide a reliable explanation for recommendation results.
12-Review based RS:
some articles about review or text based recommendations.
13-Conversational RS:
some papers made use of natural language processing technology to interactively provide recommendations.
14-Industrial RS:
some papers on best practices published in industry.
15-Privacy&Security RS:
some papers about privacy preserving and security in recommder systems.
16-LLM for RS:
some papers about large language models in recommder systems.
'Recommender Systems' 카테고리의 다른 글
| Collaborative Filtering Python Implementation (0) | 2024.04.22 |
|---|---|
| Basic Collaborative Filtering Models (0) | 2024.04.15 |
| 추천 시스템 소개 (0) | 2024.01.31 |
