HPHuy Hieu Pham

Huy Hieu Pham

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huy Hieu Pham has a total of 205 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Single-Stage Hierarchical Rectification for Weakly Supervised Histopathology Segmentation

    by Trong Duc Nguyen, Hoang Long Nguyen, Thanh Ha Do, Huy Hieu Pham

  • Open Access

    FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems

    by Quang-Tu Pham, Hoang-Dieu Vu, Dinh-Dat Pham, Hieu H. Pham

    This paper introduces FedKDX, a federated learning framework that addresses limitations in healthcare AI through Negative Knowledge Distillation (NKD). Unlike existing approaches that focus solely on positive knowledge transfer, FedKDX captures both target and non-target information to improve model generalization in healthcare applications. The framework integrates multiple knowledge transfer techniques--including traditional knowledge distillation, contrastive learning, and NKD--within a unified architecture that maintains privacy while reducing communication costs. Through experiments on healthcare datasets (SLEEP, UCI-HAR, and PAMAP2), FedKDX demonstrates improved accuracy (up to 2.53% over state-of-the-art methods), faster convergence, and better performance on non-IID data distributions. Theoretical analysis supports NKD's contribution to addressing statistical heterogeneity in distributed healthcare data. The approach shows promise for privacy-sensitive medical applications under regulatory frameworks like HIPAA and GDPR, offering a balanced solution between performance and practical implementation requirements in decentralized healthcare settings. The code and model are available at https://github.com/phamdinhdat-ai/Fed_2024.

  • Open Access

    Algorithmic iterative reticular synthesis of zeolitic imidazolate framework crystals

    by Zichao Rong, Zihao Chen, Felix Luong, Saumil Chheda, H. T. Nhan Luong, Zhiling Zheng, Kevin Greco, Abdullah A. Alghamdi, K. Huyen Bui, Théo Jaffrelot Inizan, et al.

    The discovery of crystalline reticular materials remains largely trial-and-error despite their societal importance. We introduce our algorithmic iterative reticular synthesis (AIRES) cycle, which integrates automated synthesis, image recognition, single-crystal X-ray diffraction and, crucially, customized algorithmic decision-making, to maximize distinct crystal discoveries rather than optimizing single targets. Demonstrated on zeolitic imidazolate frameworks (ZIFs), AIRES achieves twice the discovery rate of random exploration, crystallizing 10 new linkers into diverse ZIF topologies and expanding the single-linker Zn-ZIF library by one-third. By transforming reticular synthesis from an empirical process to a systematic exploration, AIRES provides a scalable and efficient blueprint for accelerating materials discovery.


  • Brain Network Analysis Based on Fine-Tuned Self-supervised Model for Brain Disease Diagnosis

    by Yifei Tang, Hongjie Jiang, Changhong Jing, Hieu Pham, Heng Lay, Nou Sotheany, Shuqiang Wang

  • Open Access

    Developing an AI-Enhanced Individualized Prediction Tool for Psychopathological Symptoms in Vietnam: A Study Protocol

    by Hung K Nguyen, Minh Khau, Huyen Nguyen, Hieu Pham

    Artificial intelligence (AI) is increasingly leveraged in mental healthcare for early detection, monitoring, and personalized intervention. However, most existing AI applications are based on categorical diagnostic systems like DSM-5 or ICD-11, which often lead to comorbidity issues, ambiguous diagnoses, and insufficient personalization. These tools typically target specific disorders (e.g., depression or anxiety), neglecting the broader, interconnected nature of psychopathological symptoms. Addressing these limitations, recent innovations in psychopathology emphasize transdiagnostic and network-based approaches, such as the Hierarchical Taxonomy of Psychopathology (HiTOP), which conceptualize mental disorders as dimensional and inter-connected constructs. This study proposes an AI-powered tool that integrates data-driven principles from both the HiTOP and symptom network models to generate individualized risk profiles for internalizing mental disorders (e.g., depression, anxiety, bipolar disorders). Our solution aims to assess individuals’ current psychopathological traits and symptom components, providing a comprehensive, nuanced profile supporting clinical diagnoses and monitoring. The study unfolds in three phases: (1) model ideation; (2) model implementation in a large-scale Vietnamese sample; and (3) deployment in clinical and psychological practice settings in Vietnam. Central to our method is the development of a Risk-aware Taxonomy-enhanced Symptom Encoder (RiTaSE), which encodes symptom data and their severities into rich representations processed via a Transformer-based model. The model is trained using high-quality, validated datasets mapped to the HiTOP framework. This project is among the first to employ AI for personalized psychopathological profiling in Vietnam,, as well as other low- and middle-income countries. Expected outcomes include an advanced diagnostic-support tool for clinical use, improved crosscultural insights into symptom comorbidity, and practical utility in mental health monitoring and intervention evaluation. Future extensions aim to broaden the scope across all HiTOP dimensions and predict transitions to clinical states through longitudinal and multi-modal data integration.

  • Noisy data-based attack: A new type of untargeted attack in Federated Learning and its countermeasures

    by Manh Cuong Dao, Phi Le Nguyen, Huy Hieu Pham, Thanh Hung Nguyen, Peng Chen, Mohamed Wahib, Thao Nguyen Truong


  • SAFA: Handling Sparse and Scarce Data in Federated Learning With Accumulative Learning

    by Nang Hung Nguyen, Truong Thao Nguyen, Trong Nghia Hoang, Hieu H. Pham, Thanh Hung Nguyen, Phi Le Nguyen

    Federated Learning (FL) has emerged as an effective paradigm allowing multiple parties to collaboratively train a global model while protecting their private data. However, it is observed that the performance of FL approaches tends to degrade significantly when data are sparsely distributed across clients with small datasets. This is referred to as the sparse-and-scarce challenge, where data held by each client is both sparse (does not contain examples to all classes) and scarce (small dataset). Sparse-and-scarce data diminishes the generalizability of clients’ data, leading to intensive over-fitting and massive domain shifts in the local models and, ultimately, decreasing the aggregated model’s performance. Interestingly, while this scenario is a specific manifestation of the well-known non-IID11This refers to the generic situation where local data distributions are not identical and independently distributed challenge in FL, it has not been distinctly addressed. Our empirical investigation highlights that generic approaches to the non-IID challenge often prove inadequate in mitigating the sparse-and-scarce issue. To bridge this gap, we develop SAFA, a novel FL algorithm that specifically addresses the sparse-and-scarce challenge via a novel continual model iteration procedure. SAFA maximally exposes local models to the inter-client diversity of data with minimal effects of catastrophic forgetting. Our experiments show that SAFA outperforms existing FL solutions, up to 17.86%, compared to the prominent baseline. The code is accessible via https://github.com/HungNguyen20/SAFA.


  • Open Access

    NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions

    by Tue M. Cao, Nhat X. Hoang, Hieu H. Pham, Phi Le Nguyen, My T. Thai

    Understanding the inner workings of neural networks is essential for enhancing model performance and interpretability. Current research predominantly focuses on examining the connection between individual neurons and the model's final predictions. Which suffers from challenges in interpreting the internal workings of the model, particularly when neurons encode multiple unrelated features. In this paper, we propose a novel framework that transitions the focus from analyzing individual neurons to investigating groups of neurons, shifting the emphasis from neuron-output relationships to functional interaction between neurons. Our automated framework, NeurFlow, first identifies core neurons and clusters them into groups based on shared functional relationships, enabling a more coherent and interpretable view of the network's internal processes. This approach facilitates the construction of a hierarchical circuit representing neuron interactions across layers, thus improving interpretability while reducing computational costs. Our extensive empirical studies validate the fidelity of our proposed NeurFlow. Additionally, we showcase its utility in practical applications such as image debugging and automatic concept labeling, thereby highlighting its potential to advance the field of neural network explainability.

  • BG-GAN: Generative AI Enable Representing Brain Structure-Function Connections for Alzheimer’s Disease

    by Tong Zhou, Chen Ding, Changhong Jing, Feng Liu, Kevin Hung, Hieu Pham, Mufti Mahmud, Zhihan Lyu, Sibo Qiao, Shuqiang Wang, et al.

    The relationship between brain structure and function is critical for revealing the pathogenesis of brain disorders, including Alzheimer’s disease (AD). However, mapping brain structure to function connections is a very challenging task. In this work, a bidirectional graph generative adversarial network (BG-GAN) is proposed to represent brain structure-function connections. Specifically, by designing a module incorporating inner graph convolution network (InnerGCN), the generators of BG-GAN can employ features of direct and indirect brain regions to learn the mapping function between the structural domain and the functional domain. Besides, a new module named Balancer is designed to counterpoise the optimization between generators and discriminators. By introducing the Balancer into BG-GAN, both the structural generator and functional generator can not only alleviate the issue of mode collapse but also learn complementarity of structural and functional features. Experimental results using Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset show that both generated structure and function connections can improve the identification accuracy of AD. The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence. They also suggest that brain structure is the basis of brain function, and the strong structural connections are majorly accompanied by strong functional connections.


  • Open Access

    Human sleep position classification using a lightweight model and acceleration data

    by Hoang-Dieu Vu, Duc-Nghia Tran, Huy-Hieu Pham, Dinh-Dat Pham, Khanh-Ly Can, To-Hieu Dao

    Purpose This exploratory study introduces a portable, wearable device using a single accelerometer to monitor twelve sleep positions. Targeted for home use, the device aims to assist patients with mild conditions such as gastroesophageal reflux disease (GERD) by tracking sleep postures, promoting healthier habits, and improving both reflux symptoms and sleep quality without requiring hospital-based monitoring. Methods The study developed AnpoNet, a lightweight deep learning model combining 1D-CNN and LSTM, optimized with BN and Dropout. The 1D-CNN captures short-term movement features, while the LSTM identifies long-term temporal dependencies. Experiments were conducted on data from 15 participants performing twelve sleep positions, with each position recorded for one minute at a sampling frequency of 50 Hz. The model was evaluated using 5-Fold cross-validation and unseen participant data to assess generalization. Results AnpoNet achieved a classification accuracy of 94.67% ± 0.80% and an F1-score of 92.94% ± 1.35%, outperforming baseline models. Accuracy was computed as the mean of accuracies obtained for three participants in the test set, averaged over five independent random seeds. This evaluation approach ensures robustness by accounting for variability in both individual participant performance and model initialization, underscoring its potential for real-world, home-based applications. Conclusion This study provides a foundation for a portable system enabling continuous, non-invasive sleep posture monitoring at home. By addressing the needs of GERD patients, the device holds promise for improving sleep quality and supporting positional therapy. Future research will focus on larger cohorts, extended monitoring durations, and user-friendly interfaces for broader adoption.