Towards ensemble learning for hybrid music recommendation

Tiemann, Marco; Pauws, Steffen

doi:10.1145/1297231.1297265

Cited by 34 publications

(17 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ensemble Recommendation: Ensemble based algorithms have been well explored to improve the performance of prediction [20,27], and are often preferred in recommendation competitions, such as the Netflix Prize contest [11,24] and KDD Cups [17,30]. Typically, an ensemble method combines the prediction of different algorithms to obtain a final prediction [18], which is often referred to as "blending" [10].…”

Section: Related Workmentioning

confidence: 99%

Ensemble contextual bandits for personalized recommendation

Tang

Jiang

et al. 2014

Proceedings of the 8th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

The cold-start problem has attracted extensive attention among various online services that provide personalized recommendation. Many online vendors employ contextual bandit strategies to tackle the so-called exploration/exploitation dilemma rooted from the cold-start problem. However, due to high-dimensional user/item features and the underlying characteristics of bandit policies, it is often difficult for service providers to obtain and deploy an appropriate algorithm to achieve acceptable and robust economic profit.In this paper, we explore ensemble strategies of contextual bandit algorithms to obtain robust predicted click-through rate (CTR) of web objects. The ensemble is acquired by aggregating different pulling policies of bandit algorithms, rather than forcing the agreement of prediction results or learning a unified predictive model. To this end, we employ a meta-bandit paradigm that places a hyper bandit over the base bandits, to explicitly explore/exploit the relative importance of base bandits based on user feedbacks. Extensive empirical experiments on two real-world data sets (news recommendation and online advertising) demonstrate the effectiveness of our proposed approach in terms of CTR.

show abstract

Section: Related Workmentioning

confidence: 99%

Ensemble contextual bandits for personalized recommendation

Tang

Jiang

et al. 2014

Proceedings of the 8th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

show abstract

“…It is necessary to consider more information in music recommendation [Celma and Lamere 2008]. Some researchers try to utilize the user rating information by applying collaborative filtering methods [Yoshii et al 2006;Li et al 2007;Tiemann and Pauws 2007;Yoshii and Goto 2009]. There are also works which exploit the information in the meta data (e.g., genre) associated with music tracks [Aucouturier and Pachet 2002;Ragno et al 2005;Pauws et al 2006].…”

Section: Motivationmentioning

confidence: 99%

“…There are several hybrid approaches combining acoustic-based and collaborative filtering music recommendation to improve the overall accuracy of predictions [Yoshii et al 2006;Li et al 2007;Tiemann and Pauws 2007;Donaldson 2007;Yoshii and Goto 2009]. Yoshii et al [2006] and Yoshii and Goto [2009] integrate both rating and music content information by using probabilistic models.…”

Section: Hybrid Music Recommendationmentioning

confidence: 99%

“…Li et al [2007] propose an item-based probabilistic model utilizing audio features to capture accurate similarities among items (i.e., music). Tiemann et al [2007] investigate ensemble learning methods for hybrid music recommendation. They apply ensemble learning methods to combine outputs of item-based collaborative filtering and acoustic-based recommendation.…”

Section: Hybrid Music Recommendationmentioning

confidence: 99%

“…In our experiment, we empirically set the value of N to be 20, and the number of nearest neighbors k to be 5, to achieve the best performance. The second compared algorithm is a acoustic-based music recommendation method [Tiemann and Pauws 2007], which uses listening relations and music similarity relations. It is denoted by AB.…”

Section: Compared Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Using Rich Social Media Information for Music Recommendation via Hypergraph Model

Tan

Chen

et al. 2011

Social Media Modeling and Computing

View full text Add to dashboard Cite

There are various kinds of social media information, including different types of objects and relations among these objects, in music social communities such as Last.fm and Pandora. This information is valuable for music recommendation. However, there are two main challenges to exploit this rich social media information: (a) There are many different types of objects and relations in music social communities, which makes it difficult to develop a unified framework taking into account all objects and relations. (b) In these communities, some relations are much more sophisticated than pairwise relation, and thus cannot be simply modeled by a graph. We propose a novel music recommendation algorithm by using both multiple kinds of social media information and music acoustic-based content. Instead of graph, we use hypergraph to model the various objects and relations, and consider music recommendation as a ranking problem on this hypergraph. While an edge of an ordinary graph connects only two objects, a hyperedge represents a set of objects. In this way, hypergraph can be naturally used to model high-order relations.

show abstract