Filters








74,980 Hits in 3.5 sec

Cross-domain Recommendation via Deep Domain Adaptation [article]

Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami, Taiji Suzuki
2018 arXiv   pre-print
To address this problem, we propose a content-based cross-domain recommendation method for cold-start users that does not require user- and item- overlap.  ...  With this formulation, the problem is reduced to a domain adaptation setting, in which a classifier trained in the source domain is adapted to the target domain.  ...  Also, Cross-domain Recommendation via Deep Domain Adaptation , , the types of items preferred by users in the target domain might be di erent from the ones in the training data. erefore, the classi er  ... 
arXiv:1803.03018v1 fatcat:pp4l375psfhite2ia7d2clhpna

2020 Index IEEE Transactions on Artificial Intelligence Vol. 1

2020 IEEE Transactions on Artificial Intelligence  
., +, TAI Aug. 2020 62-73 Self-Supervised Pose Adaptation for Cross-Domain Image Animation.  ...  ., +, TAI Oct. 2020 167-180 Self-Supervised Pose Adaptation for Cross-Domain Image Animation.  ... 
doi:10.1109/tai.2021.3089904 fatcat:53o6433ljne3lblvr5fuy66lou

A cross-domain recommender system using deep coupled autoencoders [article]

Alexandros Gkillas, Dimitrios Kosmopoulos
2022 arXiv   pre-print
Cross-domain recommendation as a domain adaptation framework has been utilized to efficiently address these challenging issues, by exploiting information from multiple domains.  ...  In light of this scenario, two novel coupled autoencoder-based deep learning methods are proposed for cross-domain recommendation.  ...  Our contribution concerns two novel coupled autoencoder-based deep learning methods for cross-domain recommendation: • The first method, dubbed CACDR (Coupled Autoencoder Cross -Domain Recommendation)  ... 
arXiv:2112.07617v3 fatcat:3g6kd7j23rgohab4j355jzyu4a

Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations [article]

Yan Zhang, Changyu Li, Ivor W. Tsang, Hui Xu, Lixin Duan, Hongzhi Yin, Wen Li, Jie Shao
2022 arXiv   pre-print
Most existing approaches attempt to solve the intractable problems via content-aware recommendations based on auxiliary information and/or cross-domain recommendations with transfer learning.  ...  learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.  ...  Cross-domain recommendations with single source domain, such as cross-domain triadic factorization (CDTF) [41] , deep domain adaptation model (DARec) [42] , and equivalent transformation learner (ETL  ... 
arXiv:2204.00327v1 fatcat:t2s4g6dxnvee5phkdracwlhefi

AutoFT: Automatic Fine-Tune for Parameters Transfer Learning in Click-Through Rate Prediction [article]

Xiangli Yang, Qing Liu, Rong Su, Ruiming Tang, Zhirong Liu, Xiuqiang He
2021 arXiv   pre-print
Recommender systems are often asked to serve multiple recommendation scenarios or domains.  ...  Fine-tuning a pre-trained CTR model from source domains and adapting it to a target domain allows knowledge transferring.  ...  Cross Domain Recommendation There are some work for cross domain recommendation that are relevant to our work.  ... 
arXiv:2106.04873v1 fatcat:pwvjsnutbfdujopr6hjzulunoi

Cross-Domain Collaborative Filtering via Translation-based Learning [article]

Dimitrios Rafailidis
2019 arXiv   pre-print
The main challenge of cross-domain recommendation is to weigh and learn users' different behaviors in multiple domains.  ...  Our experiments on six publicly available cross-domain tasks demonstrate the effectiveness of the proposed models, outperforming other state-of-the-art cross-domain strategies.  ...  in boosting the cross-domain recommendation accuracy.  ... 
arXiv:1908.06169v1 fatcat:xvblxtn4cjalzafcuk6e67jo2a

Adversarial Deep Network Embedding for Cross-network Node Classification [article]

Xiao Shen, Quanyu Dai, Fu-lai Chung, Wei Lu, Kup-Sze Choi
2020 arXiv   pre-print
This motivates us to propose an adversarial cross-network deep network embedding (ACDNE) model to integrate adversarial domain adaptation with deep network embedding so as to learn network-invariant node  ...  Moreover, an adversarial domain adaptation technique is employed to make node representations network-invariant.  ...  Recently, several deep domain adaptation algorithms have been proposed to embed domain adaptation components into deep neural networks to learn domain-invariant representations.  ... 
arXiv:2002.07366v1 fatcat:ct2225tbjrc7ri3fqk32hmknkq

Eliciting Auxiliary Information for Cold Start User Recommendation: A Survey

Nor Aniza Abdullah, Rasheed Abubakar Rasheed, Mohd Hairul Nizam Md. Nasir, Md Mujibur Rahman
2021 Applied Sciences  
Results show that auxiliary information for cold start recommendation is obtained by adapting traditional filtering and matrix factorization algorithms typically with machine learning algorithms to build  ...  This study also found that cold start user recommendation has frequently been researched in the entertainment domain, typically using music and movie data, while little research has been carried out in  ...  The study of [47] proposed a deep framework for both cross-domain and cross-system recommendations which is based on coupling deep neural network with matrix factorization models.  ... 
doi:10.3390/app11209608 fatcat:foxbu3gt4fdxhdxuhijtufkyiu

Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text [article]

Guangneng Hu, Yu Zhang, Qiang Yang
2019 arXiv   pre-print
We propose a novel neural model to smoothly enable Transfer Meeting Hybrid (TMH) methods for cross-domain recommendation with unstructured text in an end-to-end manner.  ...  TMH attentively extracts useful content from unstructured text via a memory module and selectively transfers knowledge from a source domain via a transfer network.  ...  CSN optimizes a multi-objective problem for cross-domain recommendation. This is a deep transfer learning approach for cross-domain recommendation.  ... 
arXiv:1901.07199v1 fatcat:ti7l7rv2vzca7cauwh4iidaceq

Towards Universal Sequence Representation Learning for Recommender Systems [article]

Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, Ji-Rong Wen
2022 arXiv   pre-print
With the pre-trained universal sequence representation model, our approach can be effectively transferred to new recommendation domains or platforms in a parameter-efficient way, under either inductive  ...  Especially, our approach also leads to a performance improvement in a cross-platform setting, showing the strong transferability of the proposed universal SRL method.  ...  ] pre-trains sequential models via mutual information maximization objectives for feature fusion. • CCDR [28] proposes intra-domain and inter-domain contrastive objects for cross-domain recommendation  ... 
arXiv:2206.05941v1 fatcat:2vlxpd3dt5ctnosblc7nccqwdm

A Multifaceted Model for Cross Domain Recommendation Systems [chapter]

Jianxun Lian, Fuzheng Zhang, Xing Xie, Guangzhong Sun
2017 Lecture Notes in Computer Science  
Several cross-domain RSs have been proposed in the past decade in order to reduce the sparsity issues via transferring knowledge.  ...  In this paper, we introduce a Multifaceted Cross-Domain Recommendation System (MCDRS) which incorporates two different types of collaborative filtering for cross domain RSs.  ...  Via switching the choice of source domain and target domain, we report the results of three cross domain tasks, i.e., movie → music , movie → book , and book → music .  ... 
doi:10.1007/978-3-319-63558-3_27 fatcat:kzlfi5iz5fc57hmri44z6d22ci

Adversarial Deep Network Embedding for Cross-Network Node Classification

Xiao Shen, Quanyu Dai, Fu-lai Chung, Wei Lu, Kup-Sze Choi
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This motivates us to propose an adversarial cross-network deep network embedding (ACDNE) model to integrate adversarial domain adaptation with deep network embedding so as to learn network-invariant node  ...  Moreover, an adversarial domain adaptation technique is employed to make node representations network-invariant.  ...  Recently, several deep domain adaptation algorithms have been proposed to embed domain adaptation components into deep neural networks to learn domain-invariant representations.  ... 
doi:10.1609/aaai.v34i03.5692 fatcat:zrmksxwzmzb6fo72kr4vwp3stu

One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction [article]

Xiang-Rong Sheng, Liqin Zhao, Guorui Zhou, Xinyao Ding, Binding Dai, Qiang Luo, Siran Yang, Jingshan Lv, Chi Zhang, Hongbo Deng, Xiaoqiang Zhu
2021 arXiv   pre-print
To learn an effective and efficient CTR model to handle multiple domains simultaneously, we present Star Topology Adaptive Recommender (STAR).  ...  Given requests from different business domains, STAR can adapt its parameters conditioned on the domain characteristics.  ...  To fully exploit the domain relationship, we propose Star Topology Adaptive Recommender (STAR) for multi-domain CTR prediction.  ... 
arXiv:2101.11427v5 fatcat:fhhvacticzfm3eluhmu47yjepu

Collaborative Adversarial Learning for RelationalLearning on Multiple Bipartite Graphs [article]

Jingchao Su and Xu Chen and Ya Zhang and Siheng Chen and Dan Lv and Chenyang Li
2020 arXiv   pre-print
Exploring relational learning on multiple bipartite graphs has been receiving attention because of its popular applications such as recommendations.  ...  Most existing approaches attempt to solve the sparsity problem via learning shared representations to integrate knowledge from multi-source data for shared entities.  ...  For instance, DARec [4] employs the domain adaptation technique [11] to learn domain-invariant representation via distribution matching.  ... 
arXiv:2007.08308v1 fatcat:lr7eatbmlrg4tbdazlskfzah3q

Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

Jiahao Fan, Hangyu Zhu, Xinyu Jiang, Long Meng, Chen Chen, Cong Fu, Huan Yu, Chenyun Dai, Wei Chen
2022 IEEE transactions on neural systems and rehabilitation engineering  
Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA).  ...  DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers.  ...  CONCLUSION We have illustrated a practical domain adaptation approach for deep sleep model transfer, based on statistics alignment of the deep features.  ... 
doi:10.1109/tnsre.2022.3144169 pmid:35041607 fatcat:rpqxevnbkjewhovphytiap3jcm
« Previous Showing results 1 — 15 out of 74,980 results