Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Tao Qin has a total of 166 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Knowledge Fusion and Denoising with Cross-View Contrastive Learning: A Framework for Efficient Sparse Data Processing

    by Tao Qin, Zhiqiang Huang, Xin Wang, Chenxu Wang, Pinghui Wang

    Recommender systems are effective tools to alleviate the challenges posed by information overload, but data sparsity has greatly affected their performance. Knowledge graphs (KG) can be employed to solve this problem because of their rich side information. However, existing KG-enhanced recommendation methods have the following limitations: (1) Noisy interactions: the user-item interactions constructed from implicit feedback are noisy, which is harmful to the user’s true preferences learning; (2) Insufficient fusion between different views: most KG-enhanced recommendation methods ignore the differences between signals from KG and user-item interactions and fail to fuse them effectively. To address these limitations, we propose a novel KG-enhanced recommendation framework named K nowledge F usion and D enoising with cross-view C ontrastive L earning framework (KFDCL). Specifically, we first perform contrastive learning (CL) across KG (knowledge view) and user-item interaction data (collaborative view) and then explicitly prune noisy interactions to alleviate the noisy interactions problem. Additionally, we design a weighted fusion strategy based on the activity of users and items to fuse the signals from different views adaptively. Extensive experiments on three public datasets demonstrate the effectiveness of the proposed KFDCL, notably with an average improvement of 3.79% performance over state-of-the-art methods on Recall@20 and NDCG@20.

  • Open Access

    Knowledge-Variational Contrastive Learning for Recommendation

    by Zhiqiang Huang, Tao Qin, Xin Wang, Pinghui Wang, Kuiyu Zhu

    Recommender systems are effective tools to alleviate the challenges posed by information overload, but data sparsity has greatly affected their performance. Knowledge Graphs (KGs) and self-supervised learning are used to alleviate the data sparsity problem. However, existing KG-enhanced self-supervised learning recommendation methods have the following limitations: (1) Generality : existing CL-based recommendation methods strongly rely on manually designed data augmentation strategies, leading to poor generality of the CL-based models. (2) Robustness : KG usually contains lots of task-irrelevant entities, and the user–item interactions constructed from implicit feedback are usually noisy. The noisy data will generate intrusive supervised and self-supervised signals and will degrade recommendation performance. To address these limitations, we propose a novel KG-enhanced self-supervised learning recommendation method, named Knowledge-Variational Contrastive Learning for Recommendation (KVCL) . Specifically, we first design an adaptively denoising mechanism to identify and prune the noisy data in the KG and user–item interaction bipartite graph. Then, we learn a normal distribution for each node by the variational auto-encoder, and sample multiple times from the learned distribution to obtain different contrastive views. Extensive experiments based on three public datasets show that KVCL achieves improved performance over state-of-the-art methods, notably with 3.13% performance gain over state-of-the-art methods on Recall@20 and NDCG@20. Furthermore, evaluations including ablation studies and detailed analyses of multi-scenarios, computational efficiency, complexity, and denoising interpretability further underscore its scalability and practical applicability.

  • Open Access

    SGA: Self-boosting Attributed Graph Alignment via Neighborhood Consistency-based Edge Enhancement

    by Chenxu Wang, Wencong Lin, Pinghui Wang, Tao Qin, Wei Wang, Xiaohong Guan

    Graph alignment, the task of identifying corresponding nodes across different graphs, is crucial for applications ranging from social network analysis to bioinformatics. Although most existing methods leverage graph neural networks (GNNs) to learn node embeddings for attributed graphs and match them based on node similarity, they often rely on objectives designed for node classification or link prediction. These approaches preserve node proximity within individual graphs but fail to capture cross-graph correspondence knowledge, leading to suboptimal alignment performance. This paper presents SGA (Self-boosting Graph Alignment), a novel framework that introduces a self-supervised objective and an iterative refinement scheme for robustly aligning attributed graphs. SGA begins with an unsupervised Graph Convolutional Network (GCN) to learn initial node representations. Then, a contrastive loss is designed to train the GCN using stably aligned node pairs derived from these initial embeddings. This constraint distinguishes closely connected nodes within individual graphs by leveraging cross-graph correspondence knowledge, thereby promoting accurate alignment across graphs. To handle graphs with incomplete topology, SGA incorporates an iterative refinement process enhanced by a neighborhood consistency metric. This metric evaluates the reliability of complementary edges, ensuring that only reliable connections are used to refine the graph structures. The refined graphs are then fed back into the GCN for the subsequent iterations, with the process terminating when no additional pseudo-aligned node pairs are identified or a maximum iteration count is reached. Extensive experiments on four real-world and two synthetic datasets demonstrate that SGA outperforms state-of-the-art graph alignment methods by an average of 5.8% in alignment accuracy. Our code is publicly available at https://github.com/XNetLab/SGA.

  • Open Access

    R2LED: Equipping Retrieval and Refinement in Lifelong User Modeling with Semantic IDs for CTR Prediction

    by Qidong Liu, Gengnan Wang, Zhichen Liu, Moranxin Wang, Zijian Zhang, Xiao Han, Ni Zhang, Tao Qin, Chen Li

    Lifelong user modeling, which leverages users' long-term behavior sequences for CTR prediction, has been widely applied in personalized services. Existing methods generally adopted a two-stage "retrieval-refinement" strategy to balance effectiveness and efficiency. However, they still suffer from (i) noisy retrieval due to skewed data distribution and (ii) lack of semantic understanding in refinement. While semantic enhancement, e.g., LLMs modeling or semantic embeddings, offers potential solutions to these two challenges, these approaches face impractical inference costs or insufficient representation granularity. Obsorbing multi-granularity and lightness merits of semantic identity (SID), we propose a novel paradigm that equips retrieval and refinement in Lifelong User Modeling with SEmantic IDs (R2LED) to address these issues. First, we introduce a Multi-route Mixed Retrieval for the retrieval stage. On the one hand, it captures users' interests from various granularities by several parallel recall routes. On the other hand, a mixed retrieval mechanism is proposed to efficiently retrieve candidates from both collaborative and semantic views, reducing noise. Then, for refinement, we design a Bi-level Fusion Refinement, including a target-aware cross-attention for route-level fusion and a gate mechanism for SID-level fusion. It can bridge the gap between semantic and collaborative spaces, exerting the merits of SID. The comprehensive experimental results on two public datasets demonstrate the superiority of our method in both performance and efficiency. To facilitate the reproduction, we have released the code online https://github.com/abananbao/R2LED.

  • Honokiol Inhibits Stemness in Pancreatic Cancer via Downregulating c‐Met Expression

    by Yiqun Song, Jiahui Zeng, Jiaoxing Wu, Xinlong Chen, Zhengyuan Feng, Weikun Qian, Zheng Wang, Tao Qin

    Due to its high recurrence and metastasis rates, the prognosis of pancreatic cancer (PC) patients is extremely poor. Cancer stem cells (CSCs) are the major source of occurrence and progression of PC, suggesting that targeting pancreatic CSC stemness may provide therapeutic benefits. This study aims to clarify the mechanisms by which Honokiol (HNK) inhibits the stemness of pancreatic cancer. The expression of c‐Met and downstream molecules was investigated based on public databases and also confirmed by the immunohistochemistry (IHC) staining of human tissues. Colony formation assay and sphere formation assay were conducted to verify the effect of HNK on the proliferation and stemness of PC cells. A subcutaneous transplanted tumor model of BALB/c nude mice was established to explore the effect of HNK on modulating the tumor growth of PC in vivo. c‐Met expression was significantly elevated in PC tissues versus normal pancreas tissues, and the high level of c‐Met was positively correlated with poor prognosis of PC patients. Overexpression of c‐Met significantly enhanced the proliferation and stemness of cancer cells, whereas HNK treatment reversed these effects. Critically, HNK suppressed tumor growth in vivo by downregulating c‐Met. Our study reveals that HNK reduced the proliferation and stemness of PC cells via suppressing the c‐Met overexpression. These findings provide a potential therapeutic method for PC, offering new hope for improving patients' outcomes.

  • Knowledge Graph-Enhanced Masked Auto-Encoders for Recommendation Systems

    by Zhaoli Liu, Tao Qin, Xin Wang, Qindong Sun

    Contrastive learning has received significant attention for its ability to improve the representation quality over limited labeled data, achieving notable advancements in Knowledge graphs (KGs) enhanced recommendation. However, the effectiveness of most contrastive methods heavily relies on manually designed data augmentation strategies, which often limit their generality across different datasets and downstream tasks, as well as their robustness to noise perturbations. To address these challenges, we propose a novel KG-enhanced recommendation framework named Knowledge Graph-enhanced Masked Auto-Encoders for Collaborative Filtering (KG-CMAE) based on the masking-reconstruction paradigm, which employs two types of masked auto-encoders: the Knowledge Masked Auto-Encoder (KMAE) and the Collaborative Masked Auto-Encoder (CMAE), to adaptively extract informative self-supervised signals from KGs and user-item interactions. Specifically, KMAE employs the multi-head cross-attention mechanism to reflect the importance of neighboring nodes, and selectively masks and reconstructs the important connections with high structural consistency, thereby highlighting task-relevant knowledge. CMAE focuses on masking and reconstructing the interactions with high semantic relevance in the user-item interaction graph, and incorporates an enhanced decoder to better model the direct collaborative signals, such as user-user and item-item correlations, to mitigate the over-smoothing problem. Extensive experiments are conducted on three benchmark datasets under various settings, including noisy data, cold-start user recommendation, and long-tail item recommendation. The experimental results demonstrate the effectiveness, generality and robustness of the proposed KG-CMAE model compared to various baseline methods.

  • Open Access

    Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization

    by Yuanyuan Chang, Yinghua Yao, Tao Qin, Mengmeng Wang, Ivor Tsang, Guang Dai

    Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual prompt crafting, which can be time-consuming, introduce irrelevant details, and significantly limit editing performance. In this work, we propose optimizing semantic embeddings guided by attribute classifiers to steer text-to-image models toward desired edits, without relying on text prompts or requiring any training or fine-tuning of the diffusion model. We utilize classifiers to learn precise semantic embeddings at the dataset level. The learned embeddings are theoretically justified as the optimal representation of attribute semantics, enabling disentangled and accurate edits. Experiments further demonstrate that our method achieves high levels of disentanglement and strong generalization across different domains of data. Code is available at https://github.com/Chang-yuanyuan/CASO.


  • Open Access

    Attention-based Conditional Random Field for Financial Fraud Detection

    by Xiaoguang Wang, Chenxu Wang, Luyue Zhang, Xiaole Wang, Mengqin Wang, Huanlong Liu, Tao Qin

    Financial fraud detection is critical for market transparency and regulatory compliance. Existing methods often ignore the temporal patterns in financial data, which are essential for understanding dynamic financial behaviors and detecting fraud. Moreover, they also treat companies as independent entities, overlooking the valuable interrelationships. To address these issues, we propose ACRF-RNN, a Recurrent Neural Network (RNN) with Attention-based Conditional Random Field (CRF) for fraud detection. Specifically, we use an RNN with a sliding window to capture temporal dependencies from historical data, and an attention-based CRF feature transformer to model inter-company relationships. This transforms raw financial data into optimized features, fed into a multi-layer perceptron for classification. Besides, we also use the focal loss to alleviate the class imbalance problem caused by rare fraudulent cases. This work presents a novel real-world dataset to evaluate the performance of ACRF-RNN. Extensive experiments show that ACRF-RNN outperforms the state-of-the-art methods by 15.28% in KS and 4.04% in Recall. Data and code are available at: https://github.com/XNetLab/ACRF-RNN.git.


  • Open Access

    Adversarial Propensity Weighting for Debiasing in Collaborative Filtering

    by Kuiyu Zhu, Tao Qin, Pinghui Wang, Xin Wang

    Debiased recommendation focuses on alleviating the negative impact of various biases on recommendation quality to achieve fairer personalized recommendations. Current research mainly relies on propensity score estimation or causal inference methods to alleviate selection bias; at the same time, research on prevalence bias has proposed a variety of methods based on causal graphs and contrastive learning. However, these methods have shortcomings in dealing with unstable propensity score estimates, bias interactions, and decoupling of interest and bias signals, which limits the performance improvement of recommender systems. To this end, this paper proposes APWCF, a collaborative filtering debiased method that combines dynamic propensity modeling and adversarial learning. APWCF solves the problem of high variance in propensity scores through the dynamic propensity factor, and decouples user interests and bias signals through the adversarial learning to effectively remove multiple biases. Experiments show that APWCF significantly outperforms existing methods across various benchmark datasets from different domains. Compared with the current optimal baseline PDA, Recall@10 and NDCG@10 improve by 0.10%-5.42% and 1.01%-8.60% respectively.