Hao Liu
Hongzhi Yin
Skip Abstract Section
Abstract
Cross-domain Recommendation is the task that tends to improve the recommendations in the sparse target domain by leveraging the information from other rich domains. Existing methods of cross-domain recommendation mainly focus on overlapping scenarios by assuming users are totally or partially overlapped, which are taken as bridges to connect different domains. However, this assumption does not always hold, since it is illegal to leak users’ identity information to other domains. Conducting Non-overlapping MCR (NMCR) is challenging, since (1) the absence of overlapping information prevents us from directly aligning different domains, and this situation may get worse in the MCR scenario, and (2) the distribution between source and target domains makes it difficult for us to learn common information across domains. To overcome the above challenges, we focus on NMCR and devise MCRPL as our solution. To address Challenge 1, we first learn shared domain-agnostic and domain-dependent prompts and pre-train them in the pre-training stage. To address Challenge 2, we further update the domain-dependent prompts with other parameters kept fixed to transfer the domain knowledge to the target domain. We conduct experiments on five real-world domains, and the results show the advance of our MCRPL method compared with several recent SOTA baselines. Moreover, our source codes have been publicly released.1
- [1] . 2022. Cross-domain self-attentive sequential recommendations. In Proceedings of the International Conference on Data Science and Applications. 601–614.Google Scholar
Cross Ref
- [2] . 2020. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33 (2020), 1877–1901.Google Scholar
- [3] . 2018. Tada: Trend alignment with dual-attention multi-task recurrent neural networks for sales prediction. In Proceedings of the IEEE International Conference on Data Mining. IEEE, 49–58.Google Scholar
- [4] . 2022. Intent contrastive learning for sequential recommendation. In Proceedings of the ACM International World Wide Web Conferences. 491–502.Google Scholar
- [5] . 2020. HeroGRAPH: A heterogeneous graph framework for multi-target cross-domain recommendation. In Proceedings of the ACM Conference on Recommender Systems. 1–7.Google Scholar
- [6] . 2019. Addressing the user cold start with cross-domain collaborative filtering: Exploiting item metadata in matrix factorization. User Model. User-Adapt. Interact. 29, 2 (2019), 443–486.Google ScholarDigital Library
- [7] . 2019. Cross-domain recommendation without sharing user-relevant data. In Proceedings of the ACM International World Wide Web Conferences. 491–502.Google ScholarDigital Library
- [8] . 2022. Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5). In Proceedings of the 16th ACM Conference on Recommender Systems. 299–315.Google ScholarDigital Library
- [9] . 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 249–256.Google Scholar
- [10] . 2021. DA-GCN: A domain-aware attentive graph convolution network for shared-account cross-domain sequential recommendation. In Proceedings of the International Joint Conference on Artificial Intelligence. 2483–2489.Google ScholarCross Ref
- [11] . 2023. Automated prompting for non-overlapping cross-domain sequential recommendation. arXiv:2304.04218 [cs.IR].Google Scholar
- [12] . 2022. Reinforcement learning-enhanced shared-account cross-domain sequential recommendation. IEEE Transactions on Knowledge and Data Engineering 35, 7 (2023), 7397–7411.Google Scholar
- [13] . 2022. Time interval-enhanced graph neural network for shared-account cross-domain sequential recommendation. IEEE Transactions on Neural Networks and Learning Systems (unpublished).Google Scholar
- [14] . 2023. Motif-based prompt learning for universal cross-domain recommendation. arXiv:2310.13303 [cs.IR].Google Scholar
- [15] . 2016. Session-based recommendations with recurrent neural networks. In Proceedings of the International Conference on Learning Representations. 811–820.Google Scholar
- [16] . 2019. Heterogeneous recommendation via deep low-rank sparse collective factorization. IEEE Transactions on Pattern Analysis and Machine Intelligence 42, 5 (2019), 1097–1111.Google Scholar
- [17] . 2018. Self-attentive sequential recommendation. In Proceedings of the IEEE International Conference on Data Mining. 197–206.Google ScholarCross Ref
- [18] . 2020. On sampled metrics for item recommendation. In Proceedings of the International Conference on Knowledge Discovery & Data Mining. 1748–1757.Google Scholar
- [19] . 2020. Transfer learning via contextual invariants for one-to-many cross-domain recommendation. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. 1081–1090.Google Scholar
- [20] . 2021. The power of scale for parameter-efficient prompt tuning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 3045–3059.Google Scholar
- [21] . 2009. Can movies and books collaborate? Cross-domain collaborative filtering for sparsity reduction. In Proceedings of the International Joint Conference on Artificial Intelligence.Google Scholar
- [22] . 2009. Transfer learning for collaborative filtering via a rating-matrix generative model. In Proceedings of the International Conference on Machine Learning. 617–624.Google ScholarDigital Library
- [23] . 2023. Personalized prompt learning for explainable recommendation. ACM Transactions on Information Systems 41, 4 (2023), 1–26.Google ScholarDigital Library
- [24] . 2020. Ddtcdr: Deep dual transfer cross domain recommendation. In Proceedings of the International Conference on Web Search and Data Mining. 331–339.Google ScholarDigital Library
- [25] . 2021. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the International Joint Conference on Natural Language Processing. 4582–4597.Google Scholar
- [26] . 2020. Cross domain recommendation via bi-directional transfer graph collaborative filtering networks. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 885–894.Google ScholarDigital Library
- [27] . 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surv. 55, 9 (2023), 1–35.Google ScholarDigital Library
- [28] . 2021. Leveraging distribution alignment via stein path for cross-domain cold-start recommendation. In Advances in Neural Information Processing Systems. 19223–19234.Google Scholar
- [29] . 2022. Collaborative filtering with attribution alignment for review-based non-overlapped cross domain recommendation. In Proceedings of the ACM International World Wide Web Conferences. 1181–1190.Google ScholarDigital Library
- [30] . 2022. Collaborative filtering with attribution alignment for review-based non-overlapped cross domain recommendation. In Proceedings of the ACM International World Wide Web Conferences. 1181–1190.Google ScholarDigital Library
- [31] . 2019. \(\pi\)-Net: A parallel information-sharing network for shared-account cross-domain sequential recommendations. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. 685–694.Google Scholar
- [32] . 2019. On cross-domain transfer in venue recommendation. In Proceedings of the European Conference on Information Retrieval. 443–456.Google ScholarDigital Library
- [33] . 2012. Talmud: Transfer learning for multiple domains. In Proceedings of the ACM International Conference on Information and Knowledge Management. 425–434.Google Scholar
- [34] . 2017. Argument discovery via crowdsourcing. VLDB J. 26 (2017), 511–535.Google ScholarCross Ref
- [35] . 2010. Transfer learning in collaborative filtering for sparsity reduction. In Proceedings of the AAAI Conference on Artificial Intelligence. 230–235.Google ScholarCross Ref
- [36] . 2013. Transfer learning in heterogeneous collaborative filtering domains. Artif. Intell. 197 (2013), 39–55.Google ScholarDigital Library
- [37] . 2022. Contrastive learning for representation degeneration problem in sequential recommendation. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining. 813–823.Google ScholarDigital Library
- [38] . 2019. Rethinking the item order in session-based recommendation with graph neural networks. In Proceedings of the International Conference on Information and Knowledge Management. 579–588.Google Scholar
- [39] . 2020. GAG: Global attributed graph neural network for streaming session-based recommendation. In Proceedings of the International Conference on Research and Development in Information Retrieval. 669–678.Google Scholar
- [40] . 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 1 (2020), 5485–5551.Google ScholarDigital Library
- [41] . 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the Conference on Uncertainty in Artificial Intelligence. 452–461.Google ScholarDigital Library
- [42] . 2010. Factorizing personalized markov chains for next-basket recommendation. In Proceedings of the ACM International World Wide Web Conferences. 811–820.Google ScholarDigital Library
- [43] . 2013. Cross-domain collaborative recommendation in a cold-start context: The impact of user profile size on the quality of recommendation. In Proceedings of the International Conference on User Modeling, Adaptation, and Personalization. 289–295.Google Scholar
- [44] . 2020. Exploiting cloze questions for few shot text classification and natural language inference. In Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics. 255–269.Google Scholar
- [45] . 2018. Demographic inference via knowledge transfer in cross-domain recommender systems. In Proceedings of the IEEE International Conference on Data Mining. 1218–1223.Google ScholarCross Ref
- [46] . 2019. BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In Proceedings of the ACM International Conference on Information and Knowledge Management. 1441–1450.Google Scholar
- [47] . 2023. Parallel split-join networks for shared account cross-domain sequential recommendations. IEEE Transactions on Knowledge and Data Engineering 35, 4 (2023), 4106–4123.Google Scholar
- [48] . 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 565–573.Google ScholarDigital Library
- [49] . 2017. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017).Google Scholar
- [50] . 2019. Recsys-dan: Discriminative adversarial networks for cross-domain recommender systems. IEEE Transactions on Neural Networks and Learning Systems 31, 8 (2019), 2731–2740.Google ScholarCross Ref
- [51] . 2023. PLATE: A prompt-enhanced paradigm for multi-scenario recommendations. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. 1498–1507.Google Scholar
- [52] . 2022. Selective fairness in recommendation via prompts. In Proceedings of the International Conference on Research and Development in Information Retrieval. 2657–2662.Google Scholar
- [53] . 2022. Personalized prompts for sequential recommendation. arXiv:2205.09666 [cs.IR].Google Scholar
- [54] . 2022. Contrastive learning for sequential recommendation. In Proceedings of the International Conference on Data Engineering. 1259–1273.Google Scholar
- [55] . 2022. Rethinking reinforcement learning for recommendation: A prompt perspective. In Proceedings of the International Conference on Research and Development in Information Retrieval. 1347–1357.Google Scholar
- [56] . 2015. Joint modeling of users’ interests and mobility patterns for point-of-interest recommendation. In Proceedings of the ACM International Conference on Multimedia. 819–822.Google Scholar
- [57] . 2020. Cross-domain recommendation with multiple sources. In Proceedings of the International Joint Conference on Neural Networks. 1–7.Google Scholar
- [58] . 2020. S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization. In Proceedings of the International Conference on Information and Knowledge Management. 1893–1902.Google Scholar
- [59] . 2022. Learning to prompt for vision-language models. Int. J. Comput. Vis. 130, 9 (2022), 2337–2348.Google ScholarDigital Library
- [60] . 2022. Filter-enhanced MLP is all you need for sequential recommendation. In Proceedings of the ACM International World Wide Web Conferences. 2388–2399.Google Scholar
- [61] . 2019. Dtcdr: A framework for dual-target cross-domain recommendation. In Proceedings of the International Conference on Information and Knowledge Management. 1533–1542.Google Scholar
- [62] . 2018. A deep framework for cross-domain and cross-system recommendations. In Proceedings of the International Joint Conference on Artificial Intelligence. 3711–3717.Google ScholarCross Ref
- [63] . 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
- [64] . 2023. A unified framework for cross-domain and cross-system recommendations. IEEE Transactions on Knowledge and Data Engineering 35, 2 (2023), 1171–1184.Google Scholar
- [65] . 2022. Progressive self-attention network with unsymmetrical positional encoding for sequential recommendation. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. 2029–2033.Google Scholar
Index Terms
- MCRPL: A Pretrain, Prompt, and Fine-tune Paradigm for Non-overlapping Many-to-one Cross-domain Recommendation
Recommendations
Contrastive Multi-view Interest Learning for Cross-domain Sequential Recommendation
Cross-domain recommendation (CDR), which leverages information collected from other domains, has been empirically demonstrated to effectively alleviate data sparsity and cold-start problems encountered in traditional recommendation systems. However, ...
Domain ranking for cross domain collaborative filtering
UMAP'12: Proceedings of the 20th international conference on User Modeling, Adaptation, and PersonalizationIn recommendation systems a variation of the cold start problem is a situation where the target user has few-to-none item ratings belonging to the target domain (e.g., movies) to base recommendations on. One way to overcome this is by basing ...
Comments