Abstract
Cross-domain recommendation aims to exploit heterogeneous information from a data-sufficient domain (source domain) to transfer knowledge to a data-scarce domain (target domain). A majority of existing methods focus on unidirectional transfer that leverages the domain-shared information to facilitate the recommendation of the target domain. Nevertheless, it is more beneficial to improve the recommendation performance of both domains simultaneously via a dual transfer learning schema, which is known as bidirectional cross-domain recommendation (BCDR). Existing BCDR methods have their limitations, since they only perform bidirectional transfer learning based on domain-shared representations while neglecting rich information that is private to each domain. In this article, we argue that users may have domain-biased preferences due to the characteristics of that domain. Namely, the domain-specific preference information also plays a critical role in the recommendation. To effectively leverage the domain-specific information, we propose a Multi-level Attention-based Domain Disentanglement framework dubbed MADD for BCDR, which explicitly leverages the attention mechanism to construct personalized preference with both domain-invariant and domain-specific features obtained by disentangling raw user embeddings. Specifically, the domain-invariant feature is exploited by domain-adversarial learning while the domain-specific feature is learned by imposing an orthogonal loss. We then conduct a reconstruction process on disentangled features to ensure semantic-sufficiency. After that, we devise a multi-level attention mechanism for these disentangled features, which determines their contributions to the final personalized user preference embedding by dynamically learning the attention scores of individual features. We train the model in a multi-task learning fashion to benefit both domains. Extensive experiments on real-world datasets demonstrate that our model significantly outperforms state-of-the-art cross-domain recommendation approaches.
- [1] . 2007. Cross-domain mediation in collaborative filtering. In Proceedings of the International Conference on User Modeling. Springer, 355–359.Google ScholarDigital Library
- [2] . 2022. Feature-level attentive ICF for recommendation. ACM Trans. Inf. Syst. 40, 4 (2022), 75:1–75:24.
DOI: DOI: Google ScholarDigital Library - [3] . 2020. Scalable deep hashing for large-scale social image retrieval. IEEE Trans. Image Process. 29 (2020), 1271–1284.Google ScholarCross Ref
- [4] . 2022. Stacked hybrid-attention and group collaborative learning for unbiased scene graph generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 19427–19436.Google ScholarCross Ref
- [5] . 2016. Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 1 (2016), 2096–2030.Google ScholarDigital Library
- [6] . 2013. Cross-domain recommendation via cluster-level latent factor model. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 161–176.Google ScholarCross Ref
- [7] . 2015. The Netflix recommender system: Algorithms, business value, and innovation. ACM Trans. Manag. Inf. Syst. 6, 4 (2015), 1–19.Google ScholarDigital Library
- [8] . 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In Proceedings of the 25th International Conference on World Wide Web. 507–517.Google ScholarDigital Library
- [9] . 2017. Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web. 173–182.Google ScholarDigital Library
- [10] . 2018. CoNet: Collaborative cross networks for cross-domain recommendation. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 667–676.Google ScholarDigital Library
- [11] . 2019. Transfer meets hybrid: A synthetic approach for cross-domain collaborative filtering with text. In Proceedings of the World Wide Web Conference. 2822–2829.Google ScholarDigital Library
- [12] . 2008. Factorization meets the neighborhood: A multifaceted collaborative filtering model. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 426–434.Google ScholarDigital Library
- [13] . 2014. Distributed representations of sentences and documents. In Proceedings of the International Conference on Machine Learning. PMLR, 1188–1196.Google Scholar
- [14] . 2022. Divergence-agnostic unsupervised domain adaptation by adversarial attacks. IEEE Trans. Pattern Anal. Mach. Intell. 44, 11 (2022), 8196–8211.
DOI: Google ScholarCross Ref - [15] . 2022. Faster domain adaptation networks. IEEE Trans. Knowl. Data Eng. 34, 12 (2022), 5770–5783.
DOI: Google ScholarCross Ref - [16] . 2020. DDTCDR: Deep dual transfer cross domain recommendation. In Proceedings of the 13th International Conference on Web Search and Data Mining. 331–339.Google ScholarDigital Library
- [17] . 2019. An end-to-end attention-based neural model for complementary clothing matching. ACM Trans. Multim. Comput. Commun. Applic. 15, 4 (2019), 1–16.Google ScholarDigital Library
- [18] . 2018. Universal representations: Towards multi-task learning & beyond. (2018). https://shikun.io/assets/files/miscellaneous/master_thesis.pdf.Google Scholar
- [19] . 2019. Online multi-modal hashing with dynamic query-adaption. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). 715–724.Google ScholarDigital Library
- [20] . 2018. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1930–1939.Google ScholarDigital Library
- [21] . 2018. Entire space multi-task model: An effective approach for estimating post-click conversion rate. In Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 1137–1140.Google ScholarDigital Library
- [22] . 2017. Cross-domain recommendation: An embedding and mapping approach. In Proceedings of the International Joint Conference on Artificial Intelligence. 2464–2470.Google ScholarCross Ref
- [23] . 2011. Sparse autoencoder. CS294A Lect. Notes 72, 2011 (2011), 1–19.Google Scholar
- [24] . 2018. Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 596–605.Google ScholarDigital Library
- [25] . 2020. MiNet: Mixed interest network for cross-domain click-through rate prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2669–2676.Google ScholarDigital Library
- [26] . 2020. Exploiting cross-session information for session-based recommendation with graph neural networks. ACM Trans. Inf. Syst. 38, 3 (2020), 22:1–22:23.
DOI: DOI: Google ScholarDigital Library - [27] . 2015. Estimating the causal impact of recommendation systems from observational data. In Proceedings of the 16th ACM Conference on Economics and Computation. 453–470.Google ScholarDigital Library
- [28] . 2018. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018).Google Scholar
- [29] . 2020. PEIA: Personality and emotion integrated attentive model for music recommendation on social media platforms. In Proceedings of the AAAI Conference on Artificial Intelligence. 206–213.Google ScholarCross Ref
- [30] . 2019. Deep collaborative filtering with multi-aspect information in heterogeneous networks. IEEE Trans. Knowl. Data Eng. 33, 4 (2019), 1413–1425.Google ScholarDigital Library
- [31] . 2008. Relational learning via collective matrix factorization. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 650–658.Google ScholarDigital Library
- [32] . 2022. Cross-domain recommendation via adversarial adaptation. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 1808–1817.Google ScholarDigital Library
- [33] . 2014. Cross domain recommendation based on multi-type media fusion. Neurocomputing 127 (2014), 124–134.Google ScholarDigital Library
- [34] . 2008. Visualizing data using t-SNE.J. Mach. Learn. Res. 9, 11 (2008).Google Scholar
- [35] . 2019. Conversion rate prediction via post-click behaviour modeling. arXiv preprint arXiv:1910.07099 (2019).Google Scholar
- [36] . 2015. Cross-domain collaborative filtering with review text. In 24th International Joint Conference on Artificial Intelligence.Google ScholarDigital Library
- [37] . 2017. Deep matrix factorization models for recommender systems.. In Proceedings of the International Joint Conference on Artificial Intelligence. 3203–3209.Google ScholarCross Ref
- [38] . 2020. Semi-supervised collaborative filtering by text-enhanced domain adaptation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2136–2144.Google ScholarDigital Library
- [39] . 2019. DARec: Deep domain adaptation for cross-domain recommendation via transferring rating patterns. arXiv preprint arXiv:1905.10760 (2019).Google Scholar
- [40] . 2018. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1059–1068.Google ScholarDigital Library
- [41] . 2019. DTCDR: A framework for dual-target cross-domain recommendation. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 1533–1542.Google ScholarDigital Library
- [42] . 2020. A deep framework for cross-domain and cross-system recommendations. arXiv preprint arXiv:2009.06215 (2020).Google Scholar
- [43] . 2020. A graphical and attentional framework for dual-target cross-domain recommendation. In Proceedings of the International Joint Conference on Artificial Intelligence. 3001–3008.Google ScholarCross Ref
- [44] . 2021. Cross-domain recommendation: Challenges, progress, and prospects. arXiv preprint arXiv:2103.01696 (2021).Google Scholar
- [45] . 2021. Transfer-meta framework for cross-domain recommendation to cold-start users. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1813–1817.Google ScholarDigital Library
Index Terms
- Multi-level Attention-based Domain Disentanglement for BCDR
Recommendations
Attention-Based Multi-view Feature Fusion for Cross-Domain Recommendation
Artificial Neural Networks and Machine Learning – ICANN 2021AbstractCross-domain recommendation can effectively alleviate the data sparsity problem in recommender systems. Existing methods for cross-domain recommendation can be roughly divided into two categories: specific-feature-based methods and sharing-feature-...
C²DR: Robust Cross-Domain Recommendation based on Causal Disentanglement
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningCross-domain recommendation aims to leverage heterogeneous information to transfers knowledge from a data-sufficient domain (source domain) to a data-scarce domain (target domain). Existing approaches mainly focus on learning single-domain user ...
A Cross-Domain Recommendation Mechanism for Cold-Start Users Based on Partial Least Squares Regression
Regular PapersRecommender systems are common in e-commerce platforms in recent years. Recommender systems are able to help users find preferential items among a large amount of products so that users’ time is saved and sellers’ profits are increased. Cross-domain ...
Comments