YLYan Luo

Yan Luo

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

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


Yan Luo has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts

    by Mengyu Wang, Weiyue Li, Ruizhi Qian, Yi Li, Yongce Li, Yunfan Long, Jiahui Cai, Yan Luo

    Large language models (LLMs) are widely explored for reasoning-intensive research tasks, yet resources for testing whether they can infer scientific conclusions from structured biomedical evidence remain limited. We introduce MedConclusion, a large-scale dataset of 5.7M PubMed structured abstracts for biomedical conclusion generation. Each instance pairs the non-conclusion sections of an abstract with the original author-written conclusion, providing naturally occurring supervision for evidence-to-conclusion reasoning. MedConclusion also includes journal-level metadata such as biomedical category and SJR, enabling subgroup analysis across biomedical domains. As an initial study, we evaluate diverse LLMs under conclusion and summary prompting settings and score outputs with both reference-based metrics and LLM-as-a-judge. We find that conclusion writing is behaviorally distinct from summary writing, strong models remain closely clustered under current automatic metrics, and judge identity can substantially shift absolute scores. MedConclusion provides a reusable data resource for studying scientific evidence-to-conclusion reasoning. Our code and data are available at: https://github.com/Harvard-AI-and-Robotics-Lab/MedConclusion.

  • On Demographic Group Fairness Guarantees in Deep Learning

    by Yan Luo, Congcong Wen, Min Shi, Hao Huang, Yi Fang, Mengyu Wang

    We present a theoretical framework analyzing the relationship between data distributions and fairness guarantees in deep learning. Our work establishes novel bounds that explicitly account for data distribution heterogeneity across demographic groups, while introducing a formal analysis framework that minimizes expected loss differences across these groups. Moreover, we derive bounds for fairness errors and convergence rates, characterizing how distributional differences between groups affect the fundamental trade-off between fairness and accuracy. Through extensive experiments on diverse datasets across various modalities (image, tabular data, and text), including FairVision (eye disease detection), CheXpert (pleural effusion detection), HAM10000 (skin lesion classification), FairFace (facial attribute recognition), ACS Income (income prediction), CivilComments-WILDS (toxic comment detection), we validate our theoretical findings and demonstrate that differences in feature distributions across demographic groups significantly impact model fairness, with performance disparities particularly pronounced in racial categories. The theoretical bounds we derive corroborate these empirical observations, providing insights into the fundamental limits of achieving fairness in deep learning models when faced with heterogeneous data distributions. This work advances our understanding of fairness in AI and provides a theoretical foundation for developing more equitable algorithms. Motivated by these theoretical insights, particularly the link between feature distribution shifts and fairness gaps, we propose Fairness-Aware Regularization (FAR), a practical training objective that directly minimizes inter-group discrepancies in feature centroids and covariances to improve equitable performance. We validate the effectiveness of FAR across all datasets considered in this study, consistently observing improvements in overall AUC, ES-AUC, and subgroup performance.


  • FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging With FairLoRA

    by Minghan Li, Congcong Wen, Yu Tian, Min Shi, Yan Luo, Hao Huang, Yi Fang, Mengyu Wang

    Fairness remains a critical concern in healthcare, where unequal access to services and treatment outcomes can adversely affect patient health. While Federated Learning (FL) presents a collaborative and privacy-preserving approach to model training, ensuring fairness is challenging due to heterogeneous data across institutions, and current research primarily addresses non-medical applications. To fill this gap, we establish the first experimental benchmark for fairness in medical FL, evaluating six representative FL methods across diverse demographic attributes and imaging modalities. We introduce FairFedMed, the first medical FL dataset specifically designed to study group fairness (i.e., consistent performance across demographic groups). It comprises two parts: FairFedMed-Oph, featuring 2D fundus and 3D OCT ophthalmology samples with six demographic attributes; and FairFedMed-Chest, which simulates real cross-institutional FL using subsets of CheXpert and MIMIC-CXR. Together, they support both simulated and real-world FL across diverse medical modalities and demographic groups. Existing FL models often underperform on medical images and overlook fairness across demographic groups. To address this, we propose FairLoRA, a fairness-aware FL framework based on SVD-based low-rank approximation. It customizes singular value matrices per demographic group while sharing singular vectors, ensuring both fairness and efficiency. Experimental results on the FairFedMed dataset demonstrate that FairLoRA not only achieves state-of-the-art performance in medical image classification but also significantly improves fairness across diverse populations. Our code and dataset can be accessible via GitHub link: https://github.com/Harvard-AI-and-Robotics-Lab/FairFedMed.


  • Open Access

    FairDiffusion: Enhancing equity in latent diffusion models via fair Bayesian perturbation

    by Yan Luo, Muhammad Osama Khan, Congcong Wen, Muhammad Muneeb Afzal, Titus Fidelis Wuermeling, Min Shi, Yu Tian, Yi Fang, Mengyu Wang

    Recent advancements in generative AI, particularly diffusion models, have proven valuable for text-to-image synthesis. In health care, these models offer immense potential in generating synthetic datasets and aiding medical training. Despite these strong performances, it remains uncertain whether the image generation quality is consistent across different demographic subgroups. To address this, we conduct a comprehensive analysis of fairness in medical text-to-image diffusion models. Evaluations of the Stable Diffusion model reveal substantial disparities across gender, race, and ethnicity. To reduce these biases, we propose FairDiffusion, an equity-aware latent diffusion model that improves both image quality and the semantic alignment of clinical features. In addition, we design and curate FairGenMed, a dataset tailored for fairness studies in medical generative models. FairDiffusion is further assessed on HAM10000 (dermatoscopic images) and CheXpert (chest x-rays), demonstrating its effectiveness in diverse medical imaging modalities. Together, FairDiffusion and FairGenMed advance research in fair generative learning, promoting equitable benefits of generative AI in health care.


  • Learning to Predict Gradients for Semi-Supervised Continual Learning

    by Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao

    A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning (CL) is aimed toward addressing this challenge. However, there still exists a gap between CL and human learning. In particular, humans are able to continually learn from the samples associated with known or unknown labels in their daily lives, whereas existing CL and semi-supervised CL (SSCL) methods assume that the training samples are associated with known labels. Specifically, we are interested in two questions: 1) how to utilize unrelated unlabeled data for the SSCL task and 2) how unlabeled data affect learning and catastrophic forgetting in the CL task. To explore these issues, we formulate a new SSCL method, which can be generically applied to existing CL models. Furthermore, we propose a novel gradient learner to learn from labeled data to predict gradients on unlabeled data. In this way, the unlabeled data can fit into the supervised CL framework. We extensively evaluate the proposed method on mainstream CL methods, adversarial CL (ACL), and semi-supervised learning (SSL) tasks. The proposed method achieves state-of-the-art performance on classification accuracy and backward transfer (BWT) in the CL setting while achieving the desired performance on classification accuracy in the SSL setting. This implies that the unlabeled images can enhance the generalizability of CL models on the predictive ability of unseen data and significantly alleviate catastrophic forgetting. The code is available at https://github.com/luoyan407/grad_prediction.git.


  • Open Access

    Equitable artificial intelligence for glaucoma screening with fair identity normalization

    by Min Shi, Yan Luo, Yu Tian, Lucy Q. Shen, Nazlee Zebardast, Mohammad Eslami, Saber Kazeminasab, Michael V. Boland, David S. Friedman, Louis R. Pasquale, et al.

    Glaucoma is the leading cause of irreversible blindness globally. Research indicates a disproportionate impact of glaucoma on racial and ethnic minorities. Existing deep learning models for glaucoma detection might not achieve equitable performance across diverse identity groups. We developed fair identify normalization (FIN) module to equalize the feature importance across different identity groups to improve model performance equity. The optical coherence tomography (OCT) measurements were used to categorize patients into glaucoma and non-glaucoma. The equity-scaled area under the receiver operating characteristic curve (ES-AUC) was adopted to quantify model performance equity. With FIN for racial groups, the overall AUC and ES-AUC increased from 0.82 to 0.85 and 0.77 to 0.81, respectively, with the AUC for Blacks increasing from 0.77 to 0.82. With FIN for ethnic groups, the overall AUC and ES-AUC increased from 0.82 to 0.84 and 0.77 to 0.80, respectively, with the AUC for Hispanics increasing from 0.75 to 0.79.


  • FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

    by Yu Tian, Congcong Wen, Min Shi, Muhammad Muneeb Afzal, Hao Huang, Muhammad Osama Khan, Yan Luo, Yi Fang, Mengyu Wang


  • Top Cited Papers

    Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization

    by Yan Luo, Yu Tian, Min Shi, Louis R. Pasquale, Lucy Q. Shen, Nazlee Zebardast, Tobias Elze, Mengyu Wang

    Fairness (also known as equity interchangeably) in machine learning is important for societal wellbeing, but limited public datasets hinder its progress. Currently, no dedicated public medical datasets with imaging data for fairness learning are available, though minority groups suffer from more health issues. To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset including 3,300 subjects with both 2D and 3D imaging data and balanced racial groups for glaucoma detection. Glaucoma is the leading cause of irreversible blindness globally with Blacks having doubled glaucoma prevalence than other races. We also propose a fair identity normalization (FIN) approach to equalize the feature importance between different identity groups. Our FIN approach is compared with various state-of-the-art fairness learning methods with superior performance in the racial, gender, and ethnicity fairness tasks with 2D and 3D imaging data, demonstrating the utilities of our dataset Harvard-GF for fairness learning. To facilitate fairness comparisons between different models, we propose an equity-scaled performance measure, which can be flexibly used to compare all kinds of performance metrics in the context of fairness. The dataset and code are publicly accessible via https://ophai.hms.harvard.edu/harvard-gf3300/.


  • Learning to Minimize the Remainder in Supervised Learning

    by Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao, Catherine Zhao

    The learning process of deep learning methods usually updates the model's parameters in multiple iterations. Each iteration can be viewed as the first-order approximation of Taylor's series expansion. The remainder, which consists of higher-order terms, is usually ignored in the learning process for simplicity. This learning scheme empowers various multimedia based applications, such as image retrieval, recommendation system, and video search. Generally, multimedia data (e.g., images) are semantics-rich and high-dimensional, hence the remainders of approximations are possibly non-zero. In this work, we consider the remainder to be informative and study how it affects the learning process. To this end, we propose a new learning approach, namely gradient adjustment learning (GAL), to leverage the knowledge learned from the past training iterations to adjust vanilla gradients, such that the remainders are minimized and the approximations are improved. The proposed GAL is model- and optimizer-agnostic, and is easy to adapt to the standard learning framework. It is evaluated on three tasks, i.e., image classification, object detection, and regression, with state-of-the-art models and optimizers. The experiments show that the proposed GAL consistently enhances the evaluated models, whereas the ablation studies validate various aspects of the proposed GAL. The code is available at \url{https://github.com/luoyan407/gradient_adjustment.git}.