YMYihong Ma

Yihong Ma

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


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


Latest Publications

  • Open Access

    ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery

    by Xiaobao Huang, Yihong Ma, Anjali Gurajapu, Jules Schleinitz, Zhichun Guo, Ting Hua, Sarah E. Reisman, Nitesh V. Chawla

    Reaction virtual screening and discovery are fundamental challenges in chemistry and material science, where traditional graph neural networks (GNNs) struggle to model multi-reactant interactions. In this work, we propose ChemHGNN, a hypergraph neural network (HGNN) framework that effectively captures high-order relationships in reaction networks. Unlike GNNs, which require constructing complete graphs for multi-reactant reactions, ChemHGNN naturally models multi-reactant reactions through hyperedges, enabling more expressive reaction representations. To address key challenges—such as combinatorial explosion, model collapse, and chemically invalid negative samples—we introduce a reaction center-aware negative sampling strategy (RCNS) and a hierarchical embedding approach combining molecule, reaction and hypergraph level features. Experiments on the USPTO dataset demonstrate that ChemHGNN significantly outperforms HGNN and GNN baselines, particularly in large-scale settings, while maintaining interpretability and chemical plausibility. Our work establishes ChemHGNN as a superior alternative for reaction virtual screening and discovery, offering a chemically informed framework for accelerating reaction discovery. Click here for GitHub repository.

  • Top Cited Papers
    Open Access

    Class-Imbalanced Learning on Graphs: A Survey

    by Yihong Ma, Yijun Tian, Nuno Moniz, Nitesh V. Chawla

    Rapid advancement in machine learning is increasing the demand for effective graph data analysis. However, real-world graph data often exhibits class imbalance, leading to poor performance of standard machine learning models on underrepresented classes. To address this, C lass- I mbalanced L earning on G raphs (CILG) has emerged as a promising solution that combines graph representation learning and class-imbalanced learning. This survey provides a comprehensive understanding of CILG’s current state-of-the-art, establishing the first systematic taxonomy of existing work and its connections to traditional imbalanced learning. We critically analyze recent advances and discuss key open problems. A continuously updated reading list of relevant articles and code implementations is available at https://github.com/yihongma/CILG-Papers .


  • Open Access

    HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks

    by Yihong Ma, Ning Yan, Jiayu Li, Masood Mortazavi, Nitesh V. Chawla

    Graphs have emerged as a natural choice to represent and analyze the intricate patterns and rich information of the Web, enabling applications such as online page classification and social recommendation. The prevailing ''pre-train, fine-tune'' paradigm has been widely adopted in graph machine learning tasks, particularly in scenarios with limited labeled nodes. However, this approach often exhibits a misalignment between the training objectives of pretext tasks and those of downstream tasks. This gap can result in the ''negative transfer'' problem, wherein the knowledge gained from pre-training adversely affects performance in the downstream tasks. The surge in prompt-based learning within Natural Language Processing (NLP) suggests the potential of adapting a ''pre-train, prompt'' paradigm to graphs as an alternative. However, existing graph prompting techniques are tailored to homogeneous graphs, neglecting the inherent heterogeneity of Web graphs. To bridge this gap, we propose HetGPT, a general post-training prompting framework to improve the predictive performance of pre-trained heterogeneous graph neural networks (HGNNs). The key is the design of a novel prompting function that integrates a virtual class prompt and a heterogeneous feature prompt, with the aim to reformulate downstream tasks to mirror pretext tasks. Moreover, HetGPT introduces a multi-view neighborhood aggregation mechanism, capturing the complex neighborhood structure in heterogeneous graphs. Extensive experiments on three benchmark datasets demonstrate HetGPT's capability to enhance the performance of state-of-the-art HGNNs on semi-supervised node classification.


  • Open Access

    Are we Making Much Progress? Revisiting Chemical Reaction Yield Prediction from an Imbalanced Regression Perspective

    by Yihong Ma, Xiaobao Huang, Bozhao Nan, Nuno Moniz, Xiangliang Zhang, Olaf Wiest, Nitesh V. Chawla

    The yield of a chemical reaction quantifies the percentage of the target product formed in relation to the reactants consumed during the chemical reaction. Accurate yield prediction can guide chemists toward selecting high-yield reactions during synthesis planning, offering valuable insights before dedicating time and resources to wet lab experiments. While recent advancements in yield prediction have led to overall performance improvement across the entire yield range, an open challenge remains in enhancing predictions for high-yield reactions, which are of greater concern to chemists. In this paper, we argue that the performance gap in high-yield predictions results from the imbalanced distribution of real-world data skewed towards low-yield reactions, often due to unreacted starting materials and inherent ambiguities in the reaction processes. Despite this data imbalance, existing yield prediction methods continue to treat different yield ranges equally, assuming a balanced training distribution. Through extensive experiments on three real-world yield prediction datasets, we emphasize the urgent need to reframe reaction yield prediction as an imbalanced regression problem. Finally, we demonstrate that incorporating simple cost-sensitive re-weighting methods can significantly enhance the performance of yield prediction models on underrepresented high-yield regions.


  • Detecting Anomalies in Small Unmanned Aerial Systems via Graphical Normalizing Flows

    by Yihong Ma, Nafee Al Islam, Jane Cleland-Huang, Nitesh V. Chawla

    With the increasing deployment of small Unmanned Aerial Systems (sUAS) on various tasks, it becomes crucial to analyze and detect anomalies from their flight logs. To support research in this area, we curate DLA, the first real-world time series anomaly detection dataset in the domain of sUAS, which contains 41 sUAS flight logs annotated with various types of anomalies. As anomalies tend to occur in low-density areas within a distribution, we propose Graphical Normalizing Flows (GNF), a graph-based autoregressive deep learning model, to perform anomaly detection through density estimation. GNF contains (1) a temporal encoding module using a transformer to capture the temporal dynamics, (2) an inter-feature encoding module leveraging graph representation learning on a Bayesian network to model the statistical dependencies among time series features, and (3) a density estimation module with Normalizing Flows. Extensive experiments have demonstrated GNF’s superior anomaly detection power on DLA compared with state-of-the-art baselines.


  • Open Access

    RESAM: Requirements Elicitation and Specification for Deep-Learning Anomaly Models with Applications to UAV Flight Controllers

    by Nafee Al Islam, Yihong Ma, Pedro Alarcon, Nitesh Chawla, Jane Cleland-Huang

    CyberPhysical systems (CPS) must be closely monitored to identify and potentially mitigate emergent problems that arise during their routine operations. However, the multivariate time-series data which they typically produce can be complex to understand and analyze. While formal product documentation often provides example data plots with diagnostic suggestions, the sheer diversity of attributes, critical thresholds, and data interactions can be overwhelming to non-experts who subsequently seek help from discussion forums to interpret their data logs. Deep learning models, such as Long Short-term memory (LSTM) networks can be used to automate these tasks and to provide clear explanations of diverse anomalies detected in real-time multivariate data-streams. In this paper we present RESAM, a requirements process that integrates knowledge from domain experts, discussion forums, and formal product documentation, to discover and specify requirements and design definitions in the form of time-series attributes that contribute to the construction of effective deep learning anomaly detectors. We present a case-study based on a flight control system for small Uncrewed Aerial Systems and demonstrate that its use guides the construction of effective anomaly detection models whilst also providing underlying support for explainability. RESAM is relevant to domains in which open or closed online forums provide discussion support for log analysis.


  • Open Access

    Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks

    by Yijun Tian, Chuxu Zhang, Zhichun Guo, Yihong Ma, Ronald Metoyer, Nitesh V. Chawla

    Learning effective recipe representations is essential in food studies. Unlike what has been developed for image-based recipe retrieval or learning structural text embeddings, the combined effect of multi-modal information (i.e., recipe images, text, and relation data) receives less attention. In this paper, we formalize the problem of multi-modal recipe representation learning to integrate the visual, textual, and relational information into recipe embeddings. In particular, we first present Large-RG, a new recipe graph data with over half a million nodes, making it the largest recipe graph to date. We then propose Recipe2Vec, a novel graph neural network based recipe embedding model to capture multi-modal information. Additionally, we introduce an adversarial attack strategy to ensure stable learning and improve performance. Finally, we design a joint objective function of node classification and adversarial learning to optimize the model. Extensive experiments demonstrate that Recipe2Vec outperforms state-of-the-art baselines on two classic food study tasks, i.e., cuisine category classification and region prediction. Dataset and codes are available at https://github.com/meettyj/Recipe2Vec.