Welcome to RS_c, the central platform for the RecSys community. We provide curated lists of recommender-systems datasets, algorithms, books, conferences and many resources more. Maybe most importantly, we publish the latest recommender-system news. If you want your news to be reported on RS_c, read here.
‘Microsoft Recommenders’ + ‘Linux Foundation of AI and Data’ = ‘recommenders-team’
October 30, 2023
Microsoft Recommenders was introduced a few years ago, and it provided guidelines and a collection of software libraries relating to recommender systems. Today I found the announcement that Microsoft Recommenders is joining forces with Linux Foundation of AI and Data (LF AI & Data). On GitHub, they created a new organization, “Recommenders Team“. Currently, this organization has two repositories, the “recommenders” repository, and the “artwork” repository.
Recommenders aims to aid researchers, developers, and enthusiasts in prototyping, experimenting, and transitioning both classic and advanced recommendation systems to production. It’s a project nestled under the Linux Foundation of AI and Data, housing a repository filled with exemplar practices and recommendations for constructing these systems, illustrated through Jupyter notebooks. The shared insights span five crucial tasks: data preparation for each algorithm, model building employing classical to deep learning algorithms like Alternating Least Squares (ALS) or eXtreme Deep Factorization Machines (xDeepFM), offline metric evaluation, hyperparameter tuning for model optimization, and transitioning models to a production sphere on Azure. Within Recommenders, utilities for common tasks like dataset loading as per algorithmic requirements, model output evaluation, and training/test data segmentation are provided. It encompasses implementations of several leading-edge algorithms for self-study and tailoring in individual applications, as detailed in the Recommenders documentation and further elucidated in the repository’s wiki page documents.
I am the founder of Recommender-Systems.com and head of the Intelligent Systems Group (ISG) at the University of Siegen, Germany https://isg.beel.org. We conduct research in recommender-systems (RecSys), personalization and information retrieval (IR) as well as on automated machine learning (AutoML), meta-learning and algorithm selection. Domains we are particularly interested in include smart places, eHealth, manufacturing (industry 4.0), mobility, visual computing, and digital libraries.
We founded or maintain, among others, LensKit-Auto, Darwin & Goliath, Mr. DLib, and Docear, each with thousand of users; we contributed to TensorFlow, JabRef and others; and we developed the first prototypes of automated recommender systems (AutoSurprise and Auto-CaseRec) and Federated Meta Learning (FMLearn Server and Client).