XHXinrui He

Xinrui He

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xinrui He has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SafeImpute: Reliable Clinical Data Imputation via Conformal Selection

    by Xinrui He, Mengting Ai, Junting Wang, Curtiss B. Cook, Jingrui He

  • Open Access

    FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation

    by Xinrui He, Ting-Wei Li, Tianxin Wei, Xuying Ning, Xinyu He, Wenxuan Bao, Hanghang Tong, Jingrui He

    Federated cross-domain recommendation (Federated CDR) aims to collaboratively learn personalized recommendation models across heterogeneous domains while preserving data privacy. Recently, large language model (LLM)-based recommendation models have demonstrated impressive performance by leveraging LLMs' strong reasoning capabilities and broad knowledge. However, adopting LLM-based recommendation models in Federated CDR scenarios introduces new challenges. First, there exists a risk of overfitting with domain-specific local adapters. The magnitudes of locally optimized parameter updates often vary across domains, causing biased aggregation and overfitting toward domain-specific distributions. Second, unlike traditional recommendation models (e.g., collaborative filtering, bipartite graph-based methods) that learn explicit and comparable user/item representations, LLMs encode knowledge implicitly through autoregressive text generation training. This poses additional challenges for effectively measuring the cross-domain similarities under heterogeneity. To address these challenges, we propose an LLM-based framework for federated cross-domain recommendation, FeDecider. Specifically, FeDecider tackles the challenge of scale-specific noise by disentangling each client's low-rank updates and sharing only their directional components. To handle the need for flexible and effective integration, each client further learns personalized weights that achieve the data-aware integration of updates from other domains. Extensive experiments across diverse datasets validate the effectiveness of our proposed FeDecider.


  • Open Access

    GLM-DM: language model boosted neural networks for HbA1c trend prediction in diabetes mellitus

    by Yikun Ban, Xinrui He, Patricia M. Verona, Curtiss B. Cook, Jingrui He

    Predict Hemoglobin A1c (HbA1c) trends, a key metric in diabetes mellitus (DM) management, using readily available patient variables and language models (LMs). We propose GLM (Language Model Boosted Neural Network) -DM, which leverages data augmentation and language model-driven feature encoding to predict HbA1c trends using easily accessible patient-level variables. Our model captures complex relationships among patient characteristics and enhances predictive performance through Generative Adversarial Networks (GANs) for synthetic data augmentation and LMs for feature embedding. By transforming patient profiles into rich latent representations, our approach enables a more comprehensive analysis of how patient-level variables correlate with HbA1c trends over time. Using clinical data from 257 DM patients, GLM-DM achieves 70.2% accuracy of HbA1c trend prediction, outperforming classic classifiers and transformer-based models. Ablation studies confirm the effectiveness of GAN-based augmentation and LM-driven embedding. Our model achieves 68.2% prediction accuracy for Type 1 DM and 72.7% for Type 2 DM. Proposed approach learns the underlying complex function of HbA1c using clinical variables easily available at the patient visit and leveraging the power of LMs to accurately predict the trend of HbA1c in a period. The model can enhance patient advisories for daily diabetes management without the need for continuous glucose monitoring.


  • Open Access

    PyG-SSL: A Graph Self-Supervised Learning Toolkit

    by Lecheng Zheng, Baoyu Jing, Zihao Li, Zhichen Zeng, Tianxin Wei, Mengting Ai, Xinrui He, Lihui Liu, Dongqi Fu, Jiaxuan You, et al.


  • Open Access

    Co-clustering for Federated Recommender System

    by Xinrui He, Shuo Liu, Jacky Keung, Jingrui He

    As data privacy and security attract increasing attention, Federated Recommender System (FRS) offers a solution that strikes a balance between providing high-quality recommendations and preserving user privacy. However, the presence of statistical heterogeneity in FRS, commonly observed due to personalized decision-making patterns, can pose challenges. To address this issue and maximize the benefit of collaborative filtering (CF) in FRS, it is intuitive to consider clustering clients (users) as well as items into different groups and learning group-specific models. Existing methods either resort to client clustering via user representations-risking privacy leakage, or employ classical clustering strategies on item embeddings or gradients, which we found are plagued by the curse of dimensionality. In this paper, we delve into the inefficiencies of the K-Means method in client grouping, attributing failures due to the high dimensionality as well as data sparsity occurring in FRS, and propose CoFedRec, a novel Co-clustering Federated Recommendation mechanism, to address clients heterogeneity and enhance the collaborative filtering within the federated framework. Specifically, the server initially formulates an item membership from the client-provided item networks. Subsequently, clients are grouped regarding a specific item category picked from the item membership during each communication round, resulting in an intelligently aggregated group model. Meanwhile, to comprehensively capture the global inter-relationships among items, we incorporate an additional supervised contrastive learning term based on the server-side generated item membership into the local training phase for each client. Extensive experiments on four datasets are provided, which verify the effectiveness of the proposed CoFedRec.


  • Open Access

    Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning

    by Xinrui He, Tianxin Wei, Jingrui He

    The growth of e-commerce has seen a surge in popularity of platforms like Amazon, eBay, and Taobao. This has given rise to a unique shopping behavior involving baskets - sets of items purchased together. As a less studied interaction mode in the community, the question of how should shopping basket complement personalized recommendation systems remains under-explored. While previous attempts focused on jointly modeling user purchases and baskets, the distinct semantic nature of these elements can introduce noise when directly integrated. This noise negatively impacts the model's performance, further exacerbated by significant noise (e.g., a user is misled to click an item or recognizes it as uninteresting after consuming it) within both user and basket behaviors. In order to cope with the above difficulties, we propose a novel Basket recommendation framework via Noise-tolerated Contrastive Learning, named BNCL, to handle the noise existing in the cross-behavior integration and within-behavior modeling. First, we represent the basket-item interactions as the hypergraph to model the complex basket behavior, where all items appearing in the same basket are treated as a single hyperedge. Second, cross-behavior contrastive learning is designed to suppress the noise during the fusion of diverse behaviors. Next, to further inhibit the within-behavior noise of the user and basket interactions, we propose to exploit invariant properties of the recommenders w.r.t augmentations through within-behavior contrastive learning. A novel consistency-aware augmentation approach is further designed to better identify the noisy interactions with the consideration of the above two types of interactions. Our framework BNCL offers a generic training paradigm that is applicable to different backbones. Extensive experiments on three shopping transaction datasets verify the effectiveness of our proposed method.