Multimodal Representation Learning for high-qualityRecommendations in Cold-start and Beyond-Accuracy

Recommender systems (RS) traditionally leverage the large amount of user–item interaction data. This exposes RS to a lower recom mendation quality in cold-start scenarios, as well as to a low rec ommendation quality in terms of beyond-accuracy evaluation met rics. State-of-the-art (SotA) models for cold-start scenarios rely on the use of side information on the items or the users, therefore relating recommendation to multimodal machine learning (ML). However, the mostrecent techniques from multimodal MLareoften not applied to the domain of recommendation. Additionally, the evaluation of SotA multimodal RS often neglects beyond-accuracy aspects of recommendation. In this work, we outline research into designing novel multimodal RS based on SotA multimodal ML ar chitectures for cold-start recommendation, and their evaluation and benchmark with preexisting multimodal RS in terms of accuracy and beyond-accuracy aspects of recommendation quality