IRLGJan 21, 2021

Item Recommendation from Implicit Feedback

arXiv:2101.08769v150 citations
Originality Synthesis-oriented
AI Analysis

It offers a tutorial-style review for researchers and practitioners in recommendation systems, with no incremental contributions.

This paper provides an overview of item recommendation from implicit feedback, addressing core challenges like formulating training objectives and efficient training over large item catalogues, but presents no new experimental results or concrete performance numbers.

The task of item recommendation is to select the best items for a user from a large catalogue of items. Item recommenders are commonly trained from implicit feedback which consists of past actions that are positive only. Core challenges of item recommendation are (1) how to formulate a training objective from implicit feedback and (2) how to efficiently train models over a large item catalogue. This article provides an overview of item recommendation, its unique characteristics and some common approaches. It starts with an introduction to the problem and discusses different training objectives. The main body deals with learning algorithms and presents sampling based algorithms for general recommenders and more efficient algorithms for dot product models. Finally, the application of item recommenders for retrieval tasks is discussed.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes