YaTing Zhao
YaTing Zhao has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Abdumanapov Erkhan Abdulazhanovich
Kyrgyzstan International University, Kyrgyz Republic Bishkek
1 shared publication - FengBo Wang
MianYang Polytechnic, Mianyang, China
1 shared publication - Jianhua Mei
Seokyeong University, Seoul, Republic of Korea
1 shared publication - Kambarova Zhumagul Ularbaevna
Research Institute of Innovation Economy named after Sh. Musakozhoev. Sh. Musakozhoev, Kyrgyzstan
1 shared publication Qing Hong
Doctor of Philosophy (PhD) in Management profile, Research Institute of Innovation Economy named after Sh. Musakozhoev. Sh. Musakozhoev, Kyrgyz Republic, Bishkek
1 shared publication- Rui Zhang
MianYang Polytechnic, Mianyang, China
1 shared publication
Latest Publications
- Open Access
- 18 August 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (7) , 668
HGAT-Rec: a hierarchical graph attention framework for cross-domain e-commerce recommendation with heterogeneity-aware contrastive alignment
Cross-domain recommendation over heterogeneous e-commerce networks faces three unresolved technical failures: existing GNN recommenders apply a single shared attention vector across all neighbor pairs, which can introduce a type-conflation bias governed by the inter-type variance of attention coefficients; meta-path importance weights learned in a source domain become systematically miscalibrated under the relational distribution shift of cross-domain transfer; and contrastive learning methods apply type-agnostic perturbations that assign equal dropout intensity to semantically distinct edge types, degrading representation quality in heterogeneous graph settings. We propose HGAT-Rec, which incorporates a heterogeneity-aware contrastive learning (HCL) objective that grounds view construction and sample selection in the typed relational structure of a cross-domain heterogeneous graph: type-stratified edge dropout preserves high-signal interaction channels proportionally to their attention weight, type-conditioned positive samples are drawn from meta-path neighborhoods sharing genuine relational content, and a cross-domain InfoNCE term enforces relative ordering constraints across the full overlapping user population. To support HCL, HGAT-Rec further provides (i) a type-triple-indexed graph attention mechanism parameterized by the joint combination of source node type, target node type, and edge type; (ii) a domain-conditioned meta-path aggregation layer with separate per-domain path importance distributions sharing a domain-invariant query vector; and (iii) a TransR-based knowledge gated fusion module decoupling item semantics from interaction sparsity. Theoretical grounding is provided by two formal propositions characterizing type-conflation bias and contrastive robustness under sparsity. Experiments on the Amazon Product Co-purchasing benchmark show that HGAT-Rec outperforms eleven baselines, achieving 11.20% and 8.70% improvements in NDCG@10 and HR@10 over the strongest competitor, a 31.80% gain for cold-start users, and a sparsity degradation rate of 35.2% under 80% interaction removal versus 49.0% for the next-best baseline.
- 18 August 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (7) , 668
Open AccessHGAT-Rec: a hierarchical graph attention framework for cross-domain e-commerce recommendation with heterogeneity-aware contrastive alignment
Cross-domain recommendation over heterogeneous e-commerce networks faces three unresolved technical failures: existing GNN recommenders apply a single shared attention vector across all neighbor pairs, which can introduce a type-conflation bias governed by the inter-type variance of attention coefficients; meta-path importance weights learned in a source domain become systematically miscalibrated under the relational distribution shift of cross-domain transfer; and contrastive learning methods apply type-agnostic perturbations that assign equal dropout intensity to semantically distinct edge types, degrading representation quality in heterogeneous graph settings. We propose HGAT-Rec, which incorporates a heterogeneity-aware contrastive learning (HCL) objective that grounds view construction and sample selection in the typed relational structure of a cross-domain heterogeneous graph: type-stratified edge dropout preserves high-signal interaction channels proportionally to their attention weight, type-conditioned positive samples are drawn from meta-path neighborhoods sharing genuine relational content, and a cross-domain InfoNCE term enforces relative ordering constraints across the full overlapping user population. To support HCL, HGAT-Rec further provides (i) a type-triple-indexed graph attention mechanism parameterized by the joint combination of source node type, target node type, and edge type; (ii) a domain-conditioned meta-path aggregation layer with separate per-domain path importance distributions sharing a domain-invariant query vector; and (iii) a TransR-based knowledge gated fusion module decoupling item semantics from interaction sparsity. Theoretical grounding is provided by two formal propositions characterizing type-conflation bias and contrastive robustness under sparsity. Experiments on the Amazon Product Co-purchasing benchmark show that HGAT-Rec outperforms eleven baselines, achieving 11.20% and 8.70% improvements in NDCG@10 and HR@10 over the strongest competitor, a 31.80% gain for cold-start users, and a sparsity degradation rate of 35.2% under 80% interaction removal versus 49.0% for the next-best baseline.
- Open Access
- 1 October 2025
- Published by Creative Publishing House in Architecture Image Studies
- Vol. 6 (4) , 1450-1460
Analysis Of Brand Communication Strategies Of Chinese Brands In Kyrgyzstan Market
This paper focuses on the localized communication practices of Chinese brands in the Kyrgyz market, and selects four typical cases in the fields of home appliances, telecommunications, FMCG and building materials for a cross-industry comparative study. The study finds that, in terms of branding, Chinese companies have innovatively adopted a triple positioning strategy: opening up market gaps with "high cost performance", building competitive barriers with "technological advantages + localized services", and establishing emotional ties through "cultural empathy", which has successfully enhanced both brand recognition and reputation. Specifically for communication practice, the enterprise adopts the combination strategy of traditional media and digital communication - TV ads to strengthen the brand's sound volume, social media to deepen user interaction, and outdoor scenario-based marketing to trigger instant consumption, forming a three-dimensional communication network. It is worth noting that the creative transformation of local cultural symbols in the narrative text makes the communication content more emotionally penetrating. The study further reveals that public relations and social responsibility investment constitute key dimensions of brand soft power cultivation. Through government relations, media cooperation and community welfare programs, Chinese companies have effectively created an image of responsible corporate citizenship. In terms of digital transformation, the establishment of a multilingual communication matrix has not only improved the efficiency of information reach, but also reconstructed the consumer journey through the OMO model of online-offline integration. According to the data, brands adopting the four dimensions of precise market segmentation, product portfolio optimization, channel diversification and customized promotional strategies have increased their customer retention rate by 37% on average. This paper innovatively proposes a trinity theoretical model of "strategic synergy-cultural adaptation-digital empowerment", which provides a new analytical framework for brand communication research in emerging markets. Empirical evidence shows that the model is highly applicable to explaining the effectiveness of multinational brands' localized communication, especially in the optimization of channel strategy and social media operation, which is of great practical value
- 1 October 2025
- Published by Creative Publishing House in Architecture Image Studies
- Vol. 6 (4) , 1450-1460
Open AccessAnalysis Of Brand Communication Strategies Of Chinese Brands In Kyrgyzstan Market
This paper focuses on the localized communication practices of Chinese brands in the Kyrgyz market, and selects four typical cases in the fields of home appliances, telecommunications, FMCG and building materials for a cross-industry comparative study. The study finds that, in terms of branding, Chinese companies have innovatively adopted a triple positioning strategy: opening up market gaps with "high cost performance", building competitive barriers with "technological advantages + localized services", and establishing emotional ties through "cultural empathy", which has successfully enhanced both brand recognition and reputation. Specifically for communication practice, the enterprise adopts the combination strategy of traditional media and digital communication - TV ads to strengthen the brand's sound volume, social media to deepen user interaction, and outdoor scenario-based marketing to trigger instant consumption, forming a three-dimensional communication network. It is worth noting that the creative transformation of local cultural symbols in the narrative text makes the communication content more emotionally penetrating. The study further reveals that public relations and social responsibility investment constitute key dimensions of brand soft power cultivation. Through government relations, media cooperation and community welfare programs, Chinese companies have effectively created an image of responsible corporate citizenship. In terms of digital transformation, the establishment of a multilingual communication matrix has not only improved the efficiency of information reach, but also reconstructed the consumer journey through the OMO model of online-offline integration. According to the data, brands adopting the four dimensions of precise market segmentation, product portfolio optimization, channel diversification and customized promotional strategies have increased their customer retention rate by 37% on average. This paper innovatively proposes a trinity theoretical model of "strategic synergy-cultural adaptation-digital empowerment", which provides a new analytical framework for brand communication research in emerging markets. Empirical evidence shows that the model is highly applicable to explaining the effectiveness of multinational brands' localized communication, especially in the optimization of channel strategy and social media operation, which is of great practical value