Multi-Modal Recommender Systems: Hands-On Exploration
Authors:
Open Access
- 13 September 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 834-837
Abstract
Recommender systems typically learn from user-item preference data such as ratings and clicks. This information is sparse in nature, i.e., observed user-item preferences often represent less than 5% of possible interactions. One promising direction to alleviate data sparsity is to leverage auxiliary information that may encode additional clues on how users consume items. Examples of such data (referred to as modalities) are social networks, item’s descriptive text, product images. The objective of this tutorial is to offer a comprehensive review of recent advances to represent, transform and incorporate the different modalities into recommendation models. Moreover, through practical hands-on sessions, we consider cross model/modality comparisons to investigate the importance of different methods and modalities. The hands-on exercises are conducted with Cornac (https://cornac.preferred.ai ), a comparative framework for multimodal recommender systems. The materials are made available on https://preferred.ai/recsys21-tutorial/.Keywords
Funding Information
- National Research Foundation Singapore (NRF-NRFF2016-07)
This publication has 27 references indexed in Scilit:
- What Your Images Reveal2017
- Social regularized von Mises–Fisher mixture model for item recommendationData Mining and Knowledge Discovery, 2017
- Joint Deep Modeling of Users and Items Using Reviews for Recommendation2017
- Representation Learning for Homophilic Preferences2016
- Collaborative Knowledge Base Embedding for Recommender Systems2016
- Collaborative Deep Ranking: A Hybrid Pair-Wise Recommendation Algorithm with Implicit Feedback2016
- Collaborative Deep Learning for Recommender Systems2015
- Human mobility, social ties, and link prediction2011
- Recommender systems with social regularization2011
- SoRec2008