Self-Attention Network for Session-Based Recommendation With Streaming Data Input
In the current era of the rapid development of big data, it has become increasingly critical and practical to study recommender systems with streaming data input. However, the recommender system is often faced with the challenge that the history records of new users or anonymous users are not availa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8781815/ |
| _version_ | 1818480053309145088 |
|---|---|
| author | Shiming Sun Yuanhe Tang Zemei Dai Fu Zhou |
| author_facet | Shiming Sun Yuanhe Tang Zemei Dai Fu Zhou |
| author_sort | Shiming Sun |
| collection | DOAJ |
| description | In the current era of the rapid development of big data, it has become increasingly critical and practical to study recommender systems with streaming data input. However, the recommender system is often faced with the challenge that the history records of new users or anonymous users are not available. Specifically, session-based recommendation, which aims to predict a user’s next actions, is a typical task to overcome the challenge. To capture a user’s long-term preference in session-based recommendations, recurrent neural networks (RNN)-based models have been widely applied with impressive results, but the inherent sequential nature of RNNs prevents parallelism within training examples, which is critical in long sessions because memory constraints limit batching across instances. In this paper, we propose a novel method, i.e., self-attention network for session-based recommendation (SANSR), which is based on only attention mechanisms, dispensing with recurrence, and supports parallelism in the session. The proposed model attempts to find items that are relevant based on previous time steps in the ongoing session and to assign them different weights to predict the next item. The extensive experiments are conducted on two real-world datasets, and the experimental results show that our proposed model is superior to the state-of-the-art methods. |
| first_indexed | 2024-12-10T11:18:00Z |
| format | Article |
| id | doaj.art-65ebe7988da3476caa7128051d72d7d8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-10T11:18:00Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-65ebe7988da3476caa7128051d72d7d82022-12-22T01:51:05ZengIEEEIEEE Access2169-35362019-01-01711049911050910.1109/ACCESS.2019.29319458781815Self-Attention Network for Session-Based Recommendation With Streaming Data InputShiming Sun0https://orcid.org/0000-0001-6478-2249Yuanhe Tang1Zemei Dai2Fu Zhou3NARI Group Corporation (State Grid Electric Power Research Institute), Nanjing, ChinaNARI Group Corporation (State Grid Electric Power Research Institute), Nanjing, ChinaNARI Group Corporation (State Grid Electric Power Research Institute), Nanjing, ChinaNARI Group Corporation (State Grid Electric Power Research Institute), Nanjing, ChinaIn the current era of the rapid development of big data, it has become increasingly critical and practical to study recommender systems with streaming data input. However, the recommender system is often faced with the challenge that the history records of new users or anonymous users are not available. Specifically, session-based recommendation, which aims to predict a user’s next actions, is a typical task to overcome the challenge. To capture a user’s long-term preference in session-based recommendations, recurrent neural networks (RNN)-based models have been widely applied with impressive results, but the inherent sequential nature of RNNs prevents parallelism within training examples, which is critical in long sessions because memory constraints limit batching across instances. In this paper, we propose a novel method, i.e., self-attention network for session-based recommendation (SANSR), which is based on only attention mechanisms, dispensing with recurrence, and supports parallelism in the session. The proposed model attempts to find items that are relevant based on previous time steps in the ongoing session and to assign them different weights to predict the next item. The extensive experiments are conducted on two real-world datasets, and the experimental results show that our proposed model is superior to the state-of-the-art methods.https://ieeexplore.ieee.org/document/8781815/Session-based recommendationself-attention networkstreaming data |
| spellingShingle | Shiming Sun Yuanhe Tang Zemei Dai Fu Zhou Self-Attention Network for Session-Based Recommendation With Streaming Data Input IEEE Access Session-based recommendation self-attention network streaming data |
| title | Self-Attention Network for Session-Based Recommendation With Streaming Data Input |
| title_full | Self-Attention Network for Session-Based Recommendation With Streaming Data Input |
| title_fullStr | Self-Attention Network for Session-Based Recommendation With Streaming Data Input |
| title_full_unstemmed | Self-Attention Network for Session-Based Recommendation With Streaming Data Input |
| title_short | Self-Attention Network for Session-Based Recommendation With Streaming Data Input |
| title_sort | self attention network for session based recommendation with streaming data input |
| topic | Session-based recommendation self-attention network streaming data |
| url | https://ieeexplore.ieee.org/document/8781815/ |
| work_keys_str_mv | AT shimingsun selfattentionnetworkforsessionbasedrecommendationwithstreamingdatainput AT yuanhetang selfattentionnetworkforsessionbasedrecommendationwithstreamingdatainput AT zemeidai selfattentionnetworkforsessionbasedrecommendationwithstreamingdatainput AT fuzhou selfattentionnetworkforsessionbasedrecommendationwithstreamingdatainput |