Music recommendation by unified hypergraph: combining social media information and music content

By Jiajun Bu, Shulong Tan, Chun Chen, C. Wang, Hao Wu, Lijun Zhang, Xiaofei He. ACM Multimedia, 2010

326 citations recorded by the source corpus.

Acoustic-based music recommender systems have received increasing interest in recent years. Due to the semantic gap between low level acoustic features and high level music concepts, many researchers have explored collaborative filtering techniques in music recommender systems. Traditional collaborative filtering music recommendation methods only focus on user rating information. However, 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 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. In this paper, 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. Experiments on a data set collected from the music social community Last.fm have demonstrated the effectiveness of our proposed algorithm.

Subfields: Artificial Intelligence, Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/0cd6c70ac57b796c12bd59229ea901a77ce8f066

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hongzhi Yin
2. Junliang Yu
3. Xin Xia
4. Huan Liu
5. Jundong Li
6. Li-zhen Cui
7. Xuelong Li
8. Kaize Ding

In Information Systems

1. Hongzhi Yin
2. Junliang Yu
3. Xin Xia
4. Li-zhen Cui
5. Yue Shi
6. Jundong Li
7. Nguyen Quoc Viet Hung
8. Huan Liu

In Signal Processing

1. Xuelong Li
2. Zhengjun Zha
3. Yue Shi
4. Martha A. Larson
5. Alan Hanjalic
6. Xindong Wu
7. Jundong Li
8. Hongzhi Yin

Citations in the corpus

• Collaborative Filtering beyond the User-Item Matrix (2014, methodology): “Apart from using heuristic normalizations to attain comparable scales of edge weights [Bu et al. 2010; Clements et al. 2010a], Shi et al. [2011a] have made an attempt to address this issue by adding scalars as additional entities to the graph and introducing the interaction frequency between…”
• Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search (2013, background): “In this section, we briefly introduce the related work on social image search and hypergraph learning.”
• Visual Classification by ℓ1-Hypergraph Modeling (2015, background): “Personal use is permitted, but republication/redistribution requires IEEE permission.”
• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation (2021, background): “[5] introduce hypergraph learning to music recommender systems, which is the earliest attempt.”
• Improving Content-based and Hybrid Music Recommendation using Deep Learning (2014, unknown): “[30] and Shao et al.”
• Next-item Recommendation with Sequential Hypergraphs (2020, methodology): “In terms of modeling the correlations among various types of objects, there are early efforts [5, 21, 43, 45] in applying hypergraphs to assist conventional collaborative filtering for incorporating context information.”
• Adaptive Hypergraph Learning and its Application in Image Classification (2012, unknown): “Bu et al. [33] developed music recommendation by modeling the relationship of different entities through a hypergraph to include music, tag, and users.”
• Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation (2020, background): “There are also a few studies combining hypergraph learning with recommender systems (Bu et al. 2010; Li and Li 2013).”