Tag-Aware Personalized Recommendation Using a Deep-Semantic Similarity Model with Negative Sampling

By Zhenghua Xu, Cheng Chen, Thomas Lukasiewicz, Yishu Miao, Xiang-wu Meng. 2016

85 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

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. Yi Tay
2. Shuai Zhang
3. Aixin Sun
4. Lina Yao
5. Jürgen Ziegler
6. Jiliang Tang
7. Ming Chen
8. Xiaobing Liu

In Computer Vision and Pattern Recognition

1. Yi Tay
2. Jürgen Ziegler
3. Shuai Zhang
4. Aixin Sun
5. Jiliang Tang
6. Lina Yao
7. Ming Chen
8. Xiaobing Liu

In Information Systems

1. Yi Tay
2. Aixin Sun
3. Lina Yao
4. Shuai Zhang
5. Xiangyu Zhao
6. Jürgen Ziegler
7. Jiliang Tang
8. Benedikt Loepp

Citations in the corpus

• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations (2020, background): “Xu et al.[32][33] fused tag annotations into personalized recommendation and proposed Deep Semantic Similarity based Personalized Recommendation (DSPR).”
• Sequential User-based Recurrent Neural Network Recommendations (2017, background): “More specific data, e.g. tag-based user and item profiles, have been embedded into a deep feature space in order to approach the hardly controllable dynamics of underlying tag corpora [56].”
• Deep Learning Based Recommender System (2017, background): “Note that more advanced neural layers, such as convolution and max-pooling layers, can also be easily integrated into DSSM. Deep Semantic Similarity-Based Personalized Recommendation (DSPR) [183] is a tag-aware personalized recommender where each user xu and item xi are represented by tag annotation”