Cross-Domain Collaborative Filtering with Factorization Machines

Loni, Babak; Shi, Yue; Larson, Martha; Hanjalic, Alan

doi:10.1007/978-3-319-06028-6_72

Cited by 115 publications

(66 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…little information about the consumption of Classical music through social media), alternative approaches for the acquisition of Classical music preferences through social media should be sought. The concept of cross-domain recommendations (as shown, for instance, by Loni et al [6]) could be used; Classical and non-Classical genres can be treated as different domains and hence take advantage of the methods developed for cross-domain recommendations.…”

Section: Discussionmentioning

confidence: 99%

“…More precisely, we investigate the correlation of the listening measure distributions between the two datasets, for the same genre (intra-genre, inter-dataset) and between all genres within each dataset 6 This figure is similar for Blues, Country, Jazz, Vocal, and World; but Electronic, Folk, HipHop, Metal, Pop, and Rock show smaller values for cumulative PC at top 20 artists (between 18% and 30%). 7 These cumulative PC values on the bottom 500 artists are similar for RnB and World; smaller (around 1%) for Blues, Country, EasyListening, and Vocal; and considerably higher for Electronic, Folk, HipHop, Jazz, Metal, Pop, Rap, and Rock (between 5% and 10%).…”

Section: Correlation Between Data Sources?mentioning

confidence: 99%

See 1 more Smart Citation

Genre-based Analysis of Social Media Data on Music Listening Behavior

Schedl

Tkalčič

2014

Proceedings of the First International Workshop on Internet-Scale Multimedia Management

View full text Add to dashboard Cite

It is frequently presumed that lovers of Classical music are not present in social media. In this paper, we investigate whether this statement can be empirically verified. To this end, we compare two social media platforms -Last.fm and Twitter -and perform a study on musical preference of their respective users. We investigate two research hypotheses: (i) Classical music fan are more reluctant to use social media to indicate their listing habits than listeners of other genres and (ii) there are correlations between the use of Last.fm and Twitter to indicate music listening behavior. Both hypotheses are verified and substantial differences could be made out for Twitter users. The results of these investigations will help improve music recommendation systems for listeners with non-mainstream music taste.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Correlation Between Data Sources?mentioning

confidence: 99%

Genre-based Analysis of Social Media Data on Music Listening Behavior

Schedl

Tkalčič

2014

Proceedings of the First International Workshop on Internet-Scale Multimedia Management

View full text Add to dashboard Cite

show abstract

“…Another set of research efforts focused on cross-domain recommendations which model users in a given domain and employ the model in a target domain. Works described in [8-10, 40, 41] and [42] are some examples from crossdomain recommendation systems. These systems mostly use item-based matches and do not consider users' identities or they use data from a single source and assume different categories, such as books and movies, as different domains.…”

Section: Related Workmentioning

confidence: 99%

Making recommendations by integrating information from multiple social networks

2016

View full text Add to dashboard Cite

It is becoming a common practice to use recommendation systems to serve users of web-based platforms such as social networking platforms, review web-sites, and e-commerce web-sites. Each platform produces recommendations by capturing, maintaining and analyzing data related to its users and their behavior. However, people generally use different web-based platforms for different purposes. Thus, each platform captures its own data which may reflect certain aspects related to its users. Integrating data from multiple platforms may widen the perspective of the analysis and may help in modeling users more effectively. Motivated by this, we developed a recommendation framework which integrates data collected from multiple platforms. For this purpose, we collected and anonymized datasets which contain information from several social networking and social media platforms, namely BlogCatalog, Twitter, Flickr, Facebook, YouTube and LastFm. The collected and integrated data forms a consolidated repository that may become a valuable source for researchers and practitioners. We implemented a number of recommendation methodologies to observe their performance for various cases which involve using single versus multiple features from a single source versus multiple sources. The conducted

show abstract

“…Two FMs are built for each problem and correlated with each other by sharing some common features or latent factors. Loni et al [16] applied FMs to cross-domain collaborative filtering. This method exploits knowledge from auxiliary domains to improve recommendation on a target domain, by concatenating the features from auxiliary domains and target domain.…”

Section: Related Workmentioning

confidence: 99%

Synergies that Matter: Efficient Interaction Selection via Sparse Factorization Machine

Xu¹,

Lin²,

Tan³

et al. 2016

Proceedings of the 2016 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Collaborative filtering has been widely used in modern recommender systems to provide accurate recommendations by leveraging historical interactions between users and items. The presence of cold-start items and users has imposed a huge challenge to recommender systems based on collaborative filtering, because of the unavailability of such interaction information. The factorization machine is a powerful tool designed to tackle the cold-start problems by learning a bilinear ranking model that utilizes content information about users and items, exploiting the interactions with such content information. While a factorization machine makes use of all possible interactions between all content features to make recommendations, many of the features and their interactions are not predictive of recommendations, and incorporating them in the model will deteriorate the generalization performance of the recommender systems. In this paper, we propose an efficient Sparse Factorization Machine (SFM), that simultaneously identifies relevant user and item content features, models interactions between these relevant features, and learns a bilinear model using only these synergistic interactions. We have carried out extensive empirical studies on both synthetic and real-world datasets, and compared our method to other state-of-the-art baselines, including Factorization Machine. Experimental results show that SFM can greatly outperform other baselines.

show abstract

Cross-Domain Collaborative Filtering with Factorization Machines

Cited by 115 publications

References 8 publications

Genre-based Analysis of Social Media Data on Music Listening Behavior

Genre-based Analysis of Social Media Data on Music Listening Behavior

Making recommendations by integrating information from multiple social networks

Synergies that Matter: Efficient Interaction Selection via Sparse Factorization Machine

Contact Info

Product

Resources

About