Addressing the user cold start with cross-domain collaborative filtering: exploiting item metadata in matrix factorization

User Modeling and User-Adapted Interaction (UMUAI) - jan 2019
Download the publication : Addressing the user cold start with cross-domain collaborative filtering: exploiting item metadata in matrix factorization.pdf [1.6Mo]  
Recommender systems (RS) play a focal position in modern user-centric online services. Among them, collaborative filtering (CF) approaches have shown leading accuracy performance compared to contentbased filtering (CBF) methods. Their success is due to an effective exploitation of similarities/correlations encoded in user interaction patterns, which is computed by considering common items users rated in the past. However, their strength is also their weakness. Indeed, a malicious agent can alter recommendations by adding fake user profiles into the platform thereby altering the actual similarity values in an engineered way. The spread of well-curated information available in knowledge graphs (KG) has opened the door to several new possibilities in compromising the security of a RS. In fact, KG are a wealthy source of information that can dramatically increase the attacker’s (and the defender’s) knowledge of the underlying system. In this paper, we introduce SAShA, a new attack strategy that leverages semantic features extracted from a knowledge graph in order to strengthen the efficacy of the attack to standard CF models. We performed an extensive experimental evaluation in order to investigate whether SAShA is more effective than baseline attacks against CF models by taking into account the impact of various semantic features. Experimental results on two real-world datasets show the usefulness of our strategy in favor of attacker’s capacity in attacking CF models.

BibTex references


@Article{FCTAD19,
author = {Ignacio Fern\'andez-Tob\'{\i}as and Ivan Cantador and Paolo Tomeo and Vito Walter Anelli and Tommaso {Di Noia}},
title = "Addressing the user cold start with cross-domain
collaborative filtering: exploiting item metadata
in matrix factorization",
journal = "User Modeling and User-Adapted Interaction (UMUAI)",
month = "jan",
year = "2019",
note = "https://link.springer.com/epdf/10.1007/s11257-018-
9217-6?author_access_token=NgPPZEU9MojUEQiMiUseLPe
4RwlQNchNByi7wbcMAY5o6szwXiKpRNubAEbHS563hkl_ADL5a
SC-1lj4KHSBhOPFoZavuZOKf2miHXd6pq4LUvH1H5OXUffBuNv
Keo-EQ68V712mnQDMcwdAvPBuIA%3D%3D",
url = "http://sisinflab.poliba.it/publications/2019/FCTAD
19"
}

Other publications in the database

SisInf Lab - Information Systems Laboratory

Research group of Politecnico di Bari
Edoardo Orabona St, 4 Bari, Italy