75,240 Hits in 5.7 sec

Contrastive Learning for Cold-Start Recommendation [article]

Yinwei Wei, Xiang Wang, Qi Li, Liqiang Nie, Yan Li, Xuanping Li, Tat-Seng Chua
2021 arXiv   pre-print
To model such a learning process, we devise a new objective function founded upon contrastive learning and develop a simple yet effective Contrastive Learning-based Cold-start Recommendation framework(  ...  Recommending cold-start items is a long-standing and fundamental challenge in recommender systems.  ...  Accordingly, we further develop a general cold-start recommendation framework, named Contrastive Learning-based Cold-start Recommendation, consisting of the contrastive pair organization, contrastive embedding  ... 
arXiv:2107.05315v3 fatcat:lwq6nqwpvfbx7curcnkrvwvaka

Contrastive Cross-domain Recommendation in Matching [article]

Ruobing Xie, Qi Liu, Liangdong Wang, Shukai Liu, Bo Zhang, Leyu Lin
2021 arXiv   pre-print
contrastive learning (inter-CL) tasks for better representation learning and knowledge transfer.  ...  In this work, we propose a novel Contrastive Cross-Domain Recommendation (CCDR) framework for CDR in matching.  ...  It highlights the interactions between feature fields in different domains for cold-start matching. Knowledge Distillation/Contrastive Learning Methods.  ... 
arXiv:2112.00999v1 fatcat:xyvril74izggtm5x5tha32upvu

A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation [article]

Bowen Hao, Hongzhi Yin, Jing Zhang, Cuiping Li, Hong Chen
2021 arXiv   pre-print
Cold-start problem is a fundamental challenge for recommendation tasks.  ...  The recent self-supervised learning (SSL) on Graph Neural Networks (GNNs) model, PT-GNN, pre-trains the GNN model to reconstruct the cold-start embeddings and has shown great potential for cold-start recommendation  ...  Cold-start Recommendation. Cold-start issue is a fundamental challenge in recommender systems.  ... 
arXiv:2112.02275v1 fatcat:vmdl76mcojh5rjmbmzer736w3y

Cross-domain User Preference Learning for Cold-start Recommendation [article]

Huiling Zhou, Jie Liu, Zhikang Li, Jin Yu, Hongxia Yang
2021 arXiv   pre-print
Cross-domain cold-start recommendation is an increasingly emerging issue for recommender systems.  ...  Existing works mainly focus on solving either cross-domain user recommendation or cold-start content recommendation.  ...  𝐵 . • Cold-start recommendation for inference, i.e., make recommendation on items in I ′ 𝐵 to users U 𝐴 ∪ U 𝐵 .  ... 
arXiv:2112.03667v1 fatcat:fvg2amg5qber7encbsxgosxgtu

Click-through Rate Prediction with Auto-Quantized Contrastive Learning [article]

Yujie Pan, Jiangchao Yao, Bo Han, Kunyang Jia, Ya Zhang, Hongxia Yang
2021 arXiv   pre-print
We consider this problem as an automatic identification about whether the user behaviors are rich enough to capture the interests for prediction, and propose an Auto-Quantized Contrastive Learning (AQCL  ...  Nevertheless, the current methods are struggling under the cold-start scenarios where the user interactions are extremely sparse.  ...  Auto-Quantized Contrastive Learning Self-supervision Framework for CTR In the cold-start scenarios, the click signal is usually scarce for training.  ... 
arXiv:2109.13921v1 fatcat:toaty2pz2fauznl2km7s6zj6um

ColdGAN: Resolving Cold Start User Recommendation by using Generative Adversarial Networks [article]

Po-Lin Lai, Chih-Yun Chen, Liang-Wei Lo, Chien-Chin Chen
2020 arXiv   pre-print
Mitigating the new user cold-start problem has been critical in the recommendation system for online service providers to influence user experience in decision making which can ultimately affect the intention  ...  The main idea of the proposed model is to train a network that learns the rating distributions of experienced users given their cold-start distributions.  ...  In contrast, we leverage GAN and time-based rejuvenation to generate more plausible and personalize ratings for cold-start users. Table 4 .  ... 
arXiv:2011.12566v1 fatcat:spf224yaqndgrcadeuz3x2hqwe

Latent Structures Mining with Contrastive Modality Fusion for Multimedia Recommendation [article]

Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Mengqi Zhang, Shu Wu, Liang Wang
2021 arXiv   pre-print
To be specific, we devise a novel modality-aware structure learning module, which learns item-item relationships for each modality.  ...  We argue that the latent semantic item-item structures underlying these multimodal contents could be beneficial for learning better item representations and assist the recommender models to comprehensively  ...  Performances in Cold-start Settings The cold-start problem remains a prominent challenge in recommendation systems [39] .  ... 
arXiv:2111.00678v1 fatcat:ifwywggwknahzcfyk6spo6mbu4

Intent Disentanglement and Feature Self-supervision for Novel Recommendation [article]

Tieyun Qian, Yile Liang, Qing Li, Xuan Ma, Ke Sun, Zhiyong Peng
2021 arXiv   pre-print
We further develop a new paradigm for novel recommendation of cold-start items which exploits the self-supervised learning technique to model the correlation between collaborative features and content  ...  ., cold-start items without any interaction, into consideration.  ...  for strict cold-start recommendation.  ... 
arXiv:2106.14388v1 fatcat:m4i73l45fzgzfhp7k3ud4aqc5y

Noise Contrastive Estimation for Scalable Linear Models for One-Class Collaborative Filtering [article]

Ga Wu, Maksims Volkovs, Chee Loong Soon, Scott Sanner, Himanshu Rai
2018 arXiv   pre-print
to learn personalized user models in a novel method we call NCE-PLRec leverages the improved item embedding of NCE while correcting for its popularity unbiasing in final recommendations.  ...  by linear regression methods to learn personalized recommendation models per user.  ...  Hyperparameter Tuning Training Time and Scalability Cold-Start Test Users Case Study Among the recommendation methods, PureSVD, PLRec and NCE-PLRec are able to handle cold-start recommendations without  ... 
arXiv:1811.00697v1 fatcat:vwqgqkn7lvbo5nh5r6nfasogbq

Visually Aware Skip-Gram for Image Based Recommendations [article]

Parth Tiwari, Yash Jain, Shivansh Mundra, Jenny Harding, Manoj Kumar Tiwari
2020 arXiv   pre-print
The proposed framework enables us to make personalized recommendations for cold-start products which have no purchase history.  ...  We propose a novel framework VASG (Visually Aware Skip-Gram) for learning user and product representations in a common latent space using product image features.  ...  Two subsets of the test set are created for testing in warm start and completely cold start setting: T warm = {(u, p) | u ∈ U ; p ∈ P warm } and T cold = {(u, p) | u ∈ U ; p ∈ P cold }.  ... 
arXiv:2008.06908v1 fatcat:64l4dps7z5fcbh7snpuztxyc4y

Self-supervised Recommendation with Cross-channel Matching Representation and Hierarchical Contrastive Learning [article]

Dongjie Zhu, Yundong Sun, Haiwen Du, Zhaoshuo Tian
2021 arXiv   pre-print
many experimental metrics on multiple public data sets show that the method proposed in this paper has a significant improvement compared with the state-of-the-art methods, no matter in the general or cold-start  ...  This is the first attempt in the field of recommender systems, we believe the insight of this paper is inspirational to future self-supervised learning research based on multi-channel information.  ...  For new users or items in the cold start scenario, the recommendation performance is poor due to the lack of interactive information.  ... 
arXiv:2109.00676v3 fatcat:ateh67wf7bcbxkhsevmyvlwd2m

Self-supervised Graph Learning for Occasional Group Recommendation [article]

Bowen Hao, Hongzhi Yin, Jing Zhang, Cuiping Li, Hong Chen
2021 arXiv   pre-print
We study the problem of recommending items to occasional groups (a.k.a. cold-start groups), where the occasional groups are formed ad-hoc and have few or no historical interacted items.  ...  Besides, we add a contrastive learning (CL) adapter to explicitly consider the correlations between the group and non-group members.  ...  In NeurlPS’17. 3391– Training Graph Neural Networks for Cold-Start Users and Items Representation. 3401. In WSDM’21. 265–273.  ... 
arXiv:2112.02274v1 fatcat:y75fecz3x5a7rmawhsviek4vbm

Mixing bandits

Stéphane Caron, Smriti Bhagat
2013 Proceedings of the 7th Workshop on Social Network Mining and Analysis - SNAKDD '13  
We propose two novel strategies leveraging neighborhood estimates to improve the learning rate of bandits for cold-start users.  ...  Recommending items to new or "cold-start" users is a challenging problem for recommender systems. Collaborative filtering approaches fail when the preference history of users is not available.  ...  We thank Alicia Bel and Thibaut Horel for their patience and insights in the design of the MixNeigh strategy.  ... 
doi:10.1145/2501025.2501029 dblp:conf/kdd/CaronB13 fatcat:kfskz2kdqzhg7ao44szgt6mzji

Task-adaptive Neural Process for User Cold-Start Recommendation [article]

Xixun Lin, Jia Wu, Chuan Zhou, Shirui Pan, Yanan Cao, Bin Wang
2021 arXiv   pre-print
User cold-start recommendation is a long-standing challenge for recommender systems due to the fact that only a few interactions of cold-start users can be exploited.  ...  of cold-start users more effectively.  ...  CONCLUSION In this paper, we develop a novel meta-learning model called TaNP for user cold-start recommendation.  ... 
arXiv:2103.06137v1 fatcat:cxkie6g4lfattkmrjf2ajjau3e

Collaborative Generative Hashing for Marketing and Fast Cold-start Recommendation [article]

Yan Zhang, Ivor W. Tsang, Lixin Duan
2020 arXiv   pre-print
Cold-start has being a critical issue in recommender systems with the explosion of data in e-commerce.  ...  Most existing studies proposed to alleviate the cold-start problem are also known as hybrid recommender systems that learn representations of users and items by combining user-item interactive and user  ...  Accuracy for the Cold-start Item Recommendation.  ... 
arXiv:2011.00953v1 fatcat:l643dlp2g5gsve2pv4loir45ru
« Previous Showing results 1 — 15 out of 75,240 results