Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation
Nowadays, people have an increasing interest in fresh products such as new shoes and cosmetics. To this end, an E-commerce platform Taobao launched a fresh-item hub page on the recommender system, with which customers can freely and exclusively explore and purchase fresh items, namely, the New Tende...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/8828087 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832566071583834112 |
|---|---|
| author | Zhao Li Haobo Wang Donghui Ding Shichang Hu Zhen Zhang Weiwei Liu Jianliang Gao Zhiqiang Zhang Ji Zhang |
| author_facet | Zhao Li Haobo Wang Donghui Ding Shichang Hu Zhen Zhang Weiwei Liu Jianliang Gao Zhiqiang Zhang Ji Zhang |
| author_sort | Zhao Li |
| collection | DOAJ |
| description | Nowadays, people have an increasing interest in fresh products such as new shoes and cosmetics. To this end, an E-commerce platform Taobao launched a fresh-item hub page on the recommender system, with which customers can freely and exclusively explore and purchase fresh items, namely, the New Tendency page. In this work, we make a first attempt to tackle the fresh-item recommendation task with two major challenges. First, a fresh-item recommendation scenario usually faces the challenge that the training data are highly deficient due to low page views. In this paper, we propose a deep interest-shifting network (DisNet), which transfers knowledge from a huge number of auxiliary data and then shifts user interests with contextual information. Furthermore, three interpretable interest-shifting operators are introduced. Second, since the items are fresh, many of them have never been exposed to users, leading to a severe cold-start problem. Though this problem can be alleviated by knowledge transfer, we further babysit these fully cold-start items by a relational meta-Id-embedding generator (RM-IdEG). Specifically, it trains the item id embeddings in a learning-to-learn manner and integrates relational information for better embedding performance. We conducted comprehensive experiments on both synthetic datasets as well as a real-world dataset. Both DisNet and RM-IdEG significantly outperform state-of-the-art approaches, respectively. Empirical results clearly verify the effectiveness of the proposed techniques, which are arguably promising and scalable in real-world applications. |
| format | Article |
| id | doaj-art-6e487cc9fead4756883ae5a7bccb3341 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-6e487cc9fead4756883ae5a7bccb33412025-02-03T01:05:10ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/88280878828087Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item RecommendationZhao Li0Haobo Wang1Donghui Ding2Shichang Hu3Zhen Zhang4Weiwei Liu5Jianliang Gao6Zhiqiang Zhang7Ji Zhang8Alibaba Group, Hangzhou, ChinaZhejiang University, Hangzhou, ChinaAlibaba Group, Hangzhou, ChinaAlibaba Group, Hangzhou, ChinaZhejiang University, Hangzhou, ChinaWuhan University, Wuhan, ChinaCentral South University, Changsha, ChinaZhejiang University of Finance and Economics, Hangzhou, ChinaUniversity of Southern Queensland, Toowoomba, Queensland, AustraliaNowadays, people have an increasing interest in fresh products such as new shoes and cosmetics. To this end, an E-commerce platform Taobao launched a fresh-item hub page on the recommender system, with which customers can freely and exclusively explore and purchase fresh items, namely, the New Tendency page. In this work, we make a first attempt to tackle the fresh-item recommendation task with two major challenges. First, a fresh-item recommendation scenario usually faces the challenge that the training data are highly deficient due to low page views. In this paper, we propose a deep interest-shifting network (DisNet), which transfers knowledge from a huge number of auxiliary data and then shifts user interests with contextual information. Furthermore, three interpretable interest-shifting operators are introduced. Second, since the items are fresh, many of them have never been exposed to users, leading to a severe cold-start problem. Though this problem can be alleviated by knowledge transfer, we further babysit these fully cold-start items by a relational meta-Id-embedding generator (RM-IdEG). Specifically, it trains the item id embeddings in a learning-to-learn manner and integrates relational information for better embedding performance. We conducted comprehensive experiments on both synthetic datasets as well as a real-world dataset. Both DisNet and RM-IdEG significantly outperform state-of-the-art approaches, respectively. Empirical results clearly verify the effectiveness of the proposed techniques, which are arguably promising and scalable in real-world applications.http://dx.doi.org/10.1155/2020/8828087 |
| spellingShingle | Zhao Li Haobo Wang Donghui Ding Shichang Hu Zhen Zhang Weiwei Liu Jianliang Gao Zhiqiang Zhang Ji Zhang Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation Complexity |
| title | Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation |
| title_full | Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation |
| title_fullStr | Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation |
| title_full_unstemmed | Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation |
| title_short | Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation |
| title_sort | deep interest shifting network with meta embeddings for fresh item recommendation |
| url | http://dx.doi.org/10.1155/2020/8828087 |
| work_keys_str_mv | AT zhaoli deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT haobowang deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT donghuiding deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT shichanghu deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT zhenzhang deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT weiweiliu deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT jianlianggao deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT zhiqiangzhang deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation AT jizhang deepinterestshiftingnetworkwithmetaembeddingsforfreshitemrecommendation |