Abstract
With the incredibly growing amounts of images shared on the social network, it’s necessary to ease the uses’ burden on the information overload through recommendation systems. For social image recommendation, heterogeneous information, such as image content, tags, user relationships, in addition to the user-image preferences, is extremely valuable for making effective recommendations. However, most existing social image recommendation methods mainly focus on the user-image topological structure, but largely ignore the context information. In this paper, we explore a novel algorithm for social image recommendation based on path relevance(PR). Firstly, we model both the user behaviors and image properties on a heterogeneous network and PR, a unified distance measure, is given. Then, top-k images are recommended for each personalized user through PR between user and image. Our methods can tackle the challenges of highly spares representation problem in the social network scenario. Further, an approximate method is proposed to adaptively learn the weights of different semantic edges on the heterogeneous network. We evaluate our approach with a newly collected 100,000 social image data set from Flickr. The experimental results demonstrate that our method leads to more effective recommendations, with a significant performance gain over the state-of-the-art alternatives.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Saveski, M., Mantrach, A.: Item cold-start recommendations: learning local collective embeddings, pp. 89–96 (2014)
Su, X., Khoshgoftaar, T.M.: A Survey of Collaborative Filtering Techniques. Hindawi Publishing Corp., Cairo (2009)
Salakhutdinov, R., Mnih, A.: Probabilistic matrix factorization. In: International Conference on Neural Information Processing Systems, pp. 1257–1264. Curran Associates Inc. (2007)
Li, J., Lu, K., Huang, Z., et al.: Two birds one stone: on both cold-start and long-tail recommendation. In: ACM on Multimedia Conference, pp. 898–906 (2017)
Pham, T.A.N., Li, X., Cong, G., Zhang, Z.: A general recommendation model for heterogeneous networks. IEEE Trans. Knowl. Data Eng. 28(12), 3140–3153 (2016)
Symeonidis, P., Nanopoulos, A., Manolopoulos, Y.: A unified framework for providing recommendations in social tagging systems based on ternary semantic analysis. IEEE Trans. Knowl. Data Eng. 22(2), 179–192 (2010)
Zhang, D., Zhang, D., Chang, E.Y.: Combinational collaborative filtering for personalized community recommendation. In: ACM SIGKDD, pp. 115–123 (2008)
Wang, J., Zhao, Z., Zhou, J., et al.: Recommending Flickr groups with social topic model. Inf. Retrieval 15(3–4), 278–295 (2012)
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML (2014)
Fujiwara, Y., Nakatsuji, M., Onizuka, M., et al.: Fast and exact top-k search for random walk with restart. Proc. VLDB Endow. 5(5), 442–453 (2012)
Pazzani, M.J., Billsus, D.: Content-based recommendation systems. In: Brusilovsky, P., Kobsa, A., Nejdl, W. (eds.) The Adaptive Web. LNCS, vol. 4321, pp. 325–341. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-72079-9_10
Dieleman, S., Schrauwen, B.: Deep content-based music recommendation. In: International Conference on Neural Information Processing Systems, pp. 2643–2651. Curran Associates Inc. (2013)
Hao, M., Yang, H., et al.: SoRec: social recommendation using probabilistic matrix factorization. Comput. Intell. 28(3), 931–940 (2008)
Liu, X., Tsai, M.-H., Huang, T.: Analyzing user preference for social image recommendation. arXiv preprint arXiv:1604.07044 (2016)
Zhou, X., Cui, N., Li, Z., et al.: Hierarchical gaussianization for image classification. In: IEEE, International Conference on Computer Vision. IEEE Xplore, pp. 1971–1977 (2009)
Adomavicius, G., Tuzhilin, A.: Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans. Knowl. Data Eng. 17, 734–749 (2005)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Hu, Y., Koren, Y., Volinsky, C.: Collaborative filtering for implicit feedback datasets. In: Eighth IEEE International Conference on Data Mining, pp. 263–272. IEEE (2009)
Wang, C., Blei, D.M.: Collaborative topic modeling for recommending scientific articles. In: ACM SIGKDD, pp. 448–456 (2011)
Barnard, K., Duygulu, P., Forsyth, D., et al.: Matching words and pictures. J. Mach. Learn. Res. 3(2), 1107–1135 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Chuanyan, Z., Xiaoguang, H., Zhaohui, P. (2018). Social Image Recommendation Based on Path Relevance. In: Cai, Y., Ishikawa, Y., Xu, J. (eds) Web and Big Data. APWeb-WAIM 2018. Lecture Notes in Computer Science(), vol 10987. Springer, Cham. https://doi.org/10.1007/978-3-319-96890-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-96890-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-96889-6
Online ISBN: 978-3-319-96890-2
eBook Packages: Computer ScienceComputer Science (R0)