Query：
学者姓名：檀彦超
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Recently, heterogeneous graphs have attracted widespread attention as a powerful and practical superclass of traditional homogeneous graphs, which reflect the multi-type node entities and edge relations in the real world. Most existing methods adopt meta-path construction as the mainstream to learn long-range heterogeneous semantic messages between nodes. However, such schema constructs the node-wise correlation by connecting nodes via pre-computed fixed paths, which neglects the diversities of meta-paths on the path type and path range. In this paper, we propose a meta-path-based semantic embedding schema, which is called Heterogeneous Graph Embedding with Dual Edge Differentiation (HGE-DED) to adequately construct flexible meta-path combinations thus learning the rich and discriminative semantic of target nodes. Concretely, HGEDED devises a Multi-Type and multi-Range Meta-Path Construction (MTR-MP Construction), which covers the comprehensive exploration of meta-path combinations from path type and path range, expressing the diversity of edges at more fine-grained scales. Moreover, HGE-DED designs the semantics and meta-path joint guidance, constructing a hierarchical short- and long-range relation adjustment, which constrains the path learning as well as minimizes the impact of edge heterophily on heterogeneous graphs. Experimental results on four benchmark datasets demonstrate the effectiveness of HGE-DED compared with state-of-the-art methods.
Keyword ：
Graph neural network Graph neural network Heterogeneous information network Heterogeneous information network Meta-path combination Meta-path combination Semantic embedding Semantic embedding Semi-supervised classification Semi-supervised classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Yuhong , Chen, Fuhai , Wu, Zhihao et al. Heterogeneous Graph Embedding with Dual Edge Differentiation [J]. | NEURAL NETWORKS , 2025 , 183 . |
| MLA | Chen, Yuhong et al. "Heterogeneous Graph Embedding with Dual Edge Differentiation" . | NEURAL NETWORKS 183 (2025) . |
| APA | Chen, Yuhong , Chen, Fuhai , Wu, Zhihao , Chen, Zhaoliang , Cai, Zhiling , Tan, Yanchao et al. Heterogeneous Graph Embedding with Dual Edge Differentiation . | NEURAL NETWORKS , 2025 , 183 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained; 2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Deep learning Deep learning Multi-task learning Multi-task learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Du, Shide , Fang, Zihan , Tan, Yanchao et al. OpenViewer: Openness-Aware Multi-View Learning [C] . 2025 : 16389-16397 . |
| MLA | Du, Shide et al. "OpenViewer: Openness-Aware Multi-View Learning" . (2025) : 16389-16397 . |
| APA | Du, Shide , Fang, Zihan , Tan, Yanchao , Wang, Changwei , Wang, Shiping , Guo, Wenzhong . OpenViewer: Openness-Aware Multi-View Learning . (2025) : 16389-16397 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the rapid development of Internet and Web techniques, Cross-Domain Recommendation (CDR) models have been widely explored for resolving the data-sparsity and cold-start problem. Meanwhile, most CDR models should utilize explicit domain-shareable information (e.g., overlapped users or items) for knowledge transfer across domains. However, this assumption may not be always satisfied since users and items are always non-overlapped in real practice. The performance of many previous works will be severely impaired when these domain-shareable information are not available. To address the aforementioned issues, we propose the Joint Preference Exploration and Dynamic Embedding Transportation model (JPEDET) in this paper which is a novel framework for solving the CDR problem when users and items are non-overlapped. JPEDET includes two main modules, i.e., joint preference exploration module and dynamic embedding transportation module. The joint preference exploration module aims to fuse rating and review information for modelling user preferences. The dynamic embedding transportation module is set to share knowledge via neural ordinary equations for dual transformation across domains. Moreover, we innovatively propose the dynamic transport flow equipped with linear interpolation guidance on barycentric Wasserstein path for achieving accurate and bidirectional transformation. Our empirical study on Amazon datasets demonstrates that JPEDET outperforms the state-of-the-art models under the CDR setting. Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Artificial intelligence Artificial intelligence Clock and data recovery circuits (CDR circuits) Clock and data recovery circuits (CDR circuits) Embeddings Embeddings Information dissemination Information dissemination Knowledge management Knowledge management Linear transformations Linear transformations User profile User profile
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Weiming , Chen, Chaochao , Liao, Xinting et al. Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation [C] . 2024 : 8815-8823 . |
| MLA | Liu, Weiming et al. "Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation" . (2024) : 8815-8823 . |
| APA | Liu, Weiming , Chen, Chaochao , Liao, Xinting , Hu, Mengling , Tan, Yanchao , Wang, Fan et al. Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation . (2024) : 8815-8823 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Semi-supervised graph domain adaptation, as a subfield of graph transfer learning, seeks to precisely annotate unlabeled target graph nodes by leveraging transferable features acquired from the limited labeled source nodes. However, most existing studies often directly utilize graph convolutional networks (GCNs)-based feature extractors to capture domain-invariant node features, while neglecting the issue that GCNs are insufficient in collecting complex structure information in graph. Considering the importance of graph structure information in encoding the complex relationship among nodes and edges, this paper aims to utilize such powerful information to assist graph transfer learning. To achieve this goal, we develop a novel framework called HOGDA. Concretely, HOGDA introduces a high-order structure information mixing (HSIM) module to effectively capture abundant structure information in graph, greatly enhancing the feature extractor's ability to adapt across different domains. Moreover, to achieve fine-grained feature distributions alignment, a novel strategy called adaptive weighted domain alignment (AWDA) is proposed to dynamically adjust the node weight during adversarial domain adaptation process, effectively boosting the model's transfer ability. Furthermore, to mitigate the overfitting phenomenon caused by limited source labeled nodes, we also design a trust-aware node clustering (TNC) strategy to guide the unlabeled nodes to achieve discriminative clustering. Extensive experimental results show that our HOGDA outperforms the state-of-the-art methods on various transfer tasks. © 2024 ACM.
Keyword ：
Adversarial machine learning Adversarial machine learning Self-supervised learning Self-supervised learning Semi-supervised learning Semi-supervised learning Transfer learning Transfer learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dan, Jun , Liu, Weiming , Liu, Mushui et al. HOGDA: Boosting Semi-supervised Graph Domain Adaptation via High-Order Structure-Guided Adaptive Feature Alignment [C] . 2024 : 11109-11118 . |
| MLA | Dan, Jun et al. "HOGDA: Boosting Semi-supervised Graph Domain Adaptation via High-Order Structure-Guided Adaptive Feature Alignment" . (2024) : 11109-11118 . |
| APA | Dan, Jun , Liu, Weiming , Liu, Mushui , Xie, Chunfeng , Dong, Shunjie , Ma, Guofang et al. HOGDA: Boosting Semi-supervised Graph Domain Adaptation via High-Order Structure-Guided Adaptive Feature Alignment . (2024) : 11109-11118 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Cross-Domain Recommendation has been popularly studied to resolve data sparsity problem via leveraging knowledge transfer across different domains. In this paper, we focus on the Unified Cross-Domain Recommendation (Unified CDR) problem. That is, how to enhance the recommendation performance within and cross domains when users are partially overlapped. It has two main challenges, i.e., 1) how to obtain robust matching solution among the whole users and 2) how to exploit consistent and accurate results across domains. To address these two challenges, we propose MUCRP, a cross-domain recommendation framework for the Unified CDR problem. MUCRP contains three modules, i.e., variational rating reconstruction module, robust variational embedding alignment module, and cycle-consistent preference extraction module. To solve the first challenge, we propose fused Gromov-Wasserstein distribution co-clustering optimal transport to obtain more robust matching solution via considering both semantic and structure information. To tackle the second challenge, we propose embedding-consistent and prediction-consistent losses via dual autoencoder framework to achieve consistent results. Our empirical study on Douban and Amazon datasets demonstrates that MUCRP significantly outperforms the state-of-the-art models.
Keyword ：
autoencoders autoencoders cross domain recommendation cross domain recommendation domain adaptation domain adaptation Recommendation Recommendation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, Xiaolin , Liu, Weiming , Chen, Chaochao et al. Mining User Consistent and Robust Preference for Unified Cross Domain Recommendation [J]. | IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING , 2024 , 36 (12) : 8758-8772 . |
| MLA | Zheng, Xiaolin et al. "Mining User Consistent and Robust Preference for Unified Cross Domain Recommendation" . | IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 36 . 12 (2024) : 8758-8772 . |
| APA | Zheng, Xiaolin , Liu, Weiming , Chen, Chaochao , Su, Jiajie , Liao, Xinting , Hu, Mengling et al. Mining User Consistent and Robust Preference for Unified Cross Domain Recommendation . | IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING , 2024 , 36 (12) , 8758-8772 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multimedia recommender systems (MRS) become prevalent due to their rich multimodal data (e.g., visual and textual content). Recent advancements have leveraged Graph Neural Networks (GNNs) to integrate these data, they often fall short in capturing the complex high-order relations within multimodal data, but readily hypergraph structures are not always available. To this end, we introduce the HMRec framework, a novel approach in Heterogeneous Hypergraph Structure Learning tailored for MRS. Specifically, we formulate the construction of a heterogeneous hypergraph as determining item associations across modalities, and introduce an adaptive hypergraph convolution mechanism for differentially weighting multimodal hyperedges. Furthermore, we propose an enhanced multimedia recommendation module, which introduces a contrastive fusion mechanism to effectively integrate graph-view, hypergraph-view, and ID-specific embeddings. Extensive experiments on real-world multimodal datasets show the superiority of our proposed HMRec framework in offering great potential for multimedia recommendations over the state-of-the-art baselines regarding the Recall and NDCG metrics. © 2024 IEEE.
Keyword ：
Adversarial machine learning Adversarial machine learning Contrastive Learning Contrastive Learning Federated learning Federated learning Graph embeddings Graph embeddings Graph neural networks Graph neural networks Recommender systems Recommender systems
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Tan, Yanchao , Lin, Zhenghong , Pan, Sujie et al. Heterogeneous Hypergraph Structure Learning for Multimedia Recommendation [C] . 2024 . |
| MLA | Tan, Yanchao et al. "Heterogeneous Hypergraph Structure Learning for Multimedia Recommendation" . (2024) . |
| APA | Tan, Yanchao , Lin, Zhenghong , Pan, Sujie , Xu, Siying , Liu, Weiming , Ma, Guofang et al. Heterogeneous Hypergraph Structure Learning for Multimedia Recommendation . (2024) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Continuous diagnosis prediction based on multi-modal electronic health records (EHRs) of patients is a promising yet challenging task for AI in healthcare. Existing studies ignore abundant domain knowledge of diseases (e.g., specific medical terms and their interrelations) in textual EHRs, which fails to accurately predict disease progression and assist in sequential diagnosis prediction. To this end, we first propose an Expert enhanced neural Ordinary Differential Equations (ExpertODE) framework for continuous diagnosis prediction. In particular, we first propose a novel Mixture of Language Experts (MoLE) module to enhance disease embeddings with domain knowledge. Furthermore, we propose a Contrastive Neural Ordinary Differential Equation (CNODE) module to continuously model temporal correlations of disease progression, and implement a unified contrastive learning framework to jointly optimize the domain-based MoLE module and the temporal-based CNODE module. Extensive experiments on two real-world textual EHR datasets show significant performance gains brought by our ExpertODE, yielding average improvements of 3.91% for diagnosis prediction over state-of-the-art competitors. © 2024 IEEE.
Keyword ：
Electronic health record Electronic health record Prediction models Prediction models
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Hengyu , Lv, Hang , Tan, Yanchao et al. ExpertODE: Continuous Diagnosis Prediction with Expert Enhanced Neural Ordinary Differential Equations [C] . 2024 . |
| MLA | Zhang, Hengyu et al. "ExpertODE: Continuous Diagnosis Prediction with Expert Enhanced Neural Ordinary Differential Equations" . (2024) . |
| APA | Zhang, Hengyu , Lv, Hang , Tan, Yanchao , Ma, Guofang , Wang, Fan , Yang, Carl . ExpertODE: Continuous Diagnosis Prediction with Expert Enhanced Neural Ordinary Differential Equations . (2024) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, dual-target cross-domain recommendation (DTCDR) has been proposed to alleviate the data sparsity problem by sharing the common knowledge across domains simultaneously.However, existing methods often assume that personal data containing abundant identifiable information can be directly accessed, which results in a controversial privacy leakage problem of DTCDR.To this end, we introduce the P2DTR framework, a novel approach in DTCDR while protecting private user information.Specifically, we first design a novel inter-client knowledge extraction mechanism, which exploits the private set intersection algorithm and prototype-based federated learning to enable collaboratively modeling among multiple users and a server.Furthermore, to improve the recommendation performance based on the extracted common knowledge across domains, we proposed an intra-client enhanced recommendation, consisting of a constrained dominant set (CDS) propagation mechanism and dual-recommendation module.Extensive experiments on real-world datasets validate that our proposed P2DTR framework achieves superior utility under a privacy-preserving guarantee on both domains. © 2024 International Joint Conferences on Artificial Intelligence. All rights reserved.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Zhenghong , Huang, Wei , Zhang, Hengyu et al. Enhancing Dual-Target Cross-Domain Recommendation with Federated Privacy-Preserving Learning [C] . 2024 : 2153-2161 . |
| MLA | Lin, Zhenghong et al. "Enhancing Dual-Target Cross-Domain Recommendation with Federated Privacy-Preserving Learning" . (2024) : 2153-2161 . |
| APA | Lin, Zhenghong , Huang, Wei , Zhang, Hengyu , Xu, Jiayu , Liu, Weiming , Liao, Xinting et al. Enhancing Dual-Target Cross-Domain Recommendation with Federated Privacy-Preserving Learning . (2024) : 2153-2161 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Cross-Domain Recommendation (CDR) have become increasingly appealing by leveraging useful information to tackle the data sparsity problem across domains. Most of latest CDR models assume that domain-shareable user-item information (e.g., rating and review on overlapped users or items) are accessible across domains. However, these assumptions become impractical due to the strict data privacy protection policy. In this paper, we propose Reducing Item Discrepancy (RidCDR) model on solving Privacy-Preserving Cross-Domain Recommendation (PPCDR) problem. Specifically, we aim to enhance the model performance on both source and target domains without overlapped users and items while protecting the data privacy. We innovatively propose private-robust embedding alignment module in RidCDR for knowledge sharing across domains while avoiding negative transfer privately. Our empirical study on Amazon and Douban datasets demonstrates that RidCDR significantly outperforms the state-of-the-art models under the PPCDR without overlapped users and items. Copyright 2024 by the author(s)
Keyword ：
Differential privacy Differential privacy Privacy-preserving techniques Privacy-preserving techniques
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Weiming , Zheng, Xiaolin , Chen, Chaochao et al. Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation [C] . 2024 : 32455-32470 . |
| MLA | Liu, Weiming et al. "Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation" . (2024) : 32455-32470 . |
| APA | Liu, Weiming , Zheng, Xiaolin , Chen, Chaochao , Xu, Jiahe , Liao, Xinting , Wang, Fan et al. Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation . (2024) : 32455-32470 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, dual-target cross-domain recommendation (DTCDR) has been proposed to alleviate the data sparsity problem by sharing the common knowledge across domains simultaneously. However, existing methods often assume that personal data containing abundant identifiable information can be directly accessed, which results in a controversial privacy leakage problem of DTCDR. To this end, we introduce the P2DTR framework, a novel approach in DTCDR while protecting private user information. Specifically, we first design a novel inter-client knowledge extraction mechanism, which exploits the private set intersection algorithm and prototype-based federated learning to enable collaboratively modeling among multiple users and a server. Furthermore, to improve the recommendation performance based on the extracted common knowledge across domains, we proposed an intra-client enhanced recommendation, consisting of a constrained dominant set (CDS) propagation mechanism and dual-recommendation module. Extensive experiments on real-world datasets validate that our proposed P2DTR framework achieves superior utility under a privacy-preserving guarantee on both domains.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Zhenghong , Huang, Wei , Zhang, Hengyu et al. Enhancing Dual-Target Cross-Domain Recommendation with Federated Privacy-Preserving Learning [J]. | PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024 , 2024 : 2153-2161 . |
| MLA | Lin, Zhenghong et al. "Enhancing Dual-Target Cross-Domain Recommendation with Federated Privacy-Preserving Learning" . | PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024 (2024) : 2153-2161 . |
| APA | Lin, Zhenghong , Huang, Wei , Zhang, Hengyu , Xu, Jiayu , Liu, Weiming , Liao, Xinting et al. Enhancing Dual-Target Cross-Domain Recommendation with Federated Privacy-Preserving Learning . | PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024 , 2024 , 2153-2161 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
