Name
Title | ||
|---|---|---|
Tag-Aware Personalized Recommendation Using a Deep-Semantic Similarity Model with Negative Sampling |
Abstract | ||
|---|---|---|
With the rapid growth of social tagging systems, many efforts have been put on tag-aware personalized recommendation. However, due to uncontrolled vocabularies, social tags are usually redundant, sparse, and ambiguous. In this paper, we propose a deep neural network approach to solve this problem by mapping both the tag-based user and item profiles to an abstract deep feature space, where the deep-semantic similarities between users and their target items (resp., irrelevant items) are maximized (resp., minimized). Due to huge numbers of online items, the training of this model is usually computationally expensive in the real-world context. Therefore, we introduce negative sampling, which significantly increases the model's training efficiency (109.6 times quicker) and ensures the scalability in practice. Experimental results show that our model can significantly outperform the state-of-the-art baselines in tag-aware personalized recommendation: e.g., its mean reciprocal rank is between 5.7 and 16.5 times better than the baselines. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1145/2983323.2983874 | ACM International Conference on Information and Knowledge Management |
Keywords | Field | DocType |
Tag-Aware Personalized Recommendation,Social Tagging System,Deep Neural Network,Deep-Semantic Similarity,Negative Sampling | Semantic similarity,Data mining,Feature vector,Information retrieval,Computer science,Mean reciprocal rank,Sampling (statistics),Artificial intelligence,Artificial neural network,Social tags,Machine learning,Scalability | Conference |
Citations | PageRank | References |
10 | 0.50 | 10 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhenghua Xu | 1 | 27 | 6.77 |
| Cheng Chen | 2 | 23 | 1.99 |
| Thomas Lukasiewicz | 3 | 2618 | 165.18 |
| Yishu Miao | 4 | 178 | 11.44 |
| Xiangwu Meng | 5 | 72 | 11.99 |