Hi! I'm Yangxin Fan. Currently, I am a PhD candidate in Computer Science at the Case Western Reserve University, advised by Professor. Yinghui Wu (https://yinghwu.github.io/)

My main research interests include foundamental research in Large Language Models, Graph Neural Networks, Scalable ML, Timeseries with their real-world applications in Chemistry, Computational Social Science, Health Informatics, and Material Science.

Besides research, I enjoy Photography and Spaceflight.

Publications

Computer Science

Yangxin Fan, Haolai Che, Yinghui Wu. Inference-friendly Graph Compression for Graph Neural Networks, The 51st International Conference on Very Large Data Bases (VLDB), 2025

2. Yangxin Fan, Haolai Che, Mingjian Lu, Yinghui Wu. Graph Compression for Interpretable Graph Neural Network Inference At Scale, The 51st International Conference on Very Large Data Bases (VLDB), 2025

3. Mengying Wang, Hanchao Ma, Yiyang Bian, Yangxin Fan, Yinghui Wu. Generating Skyline Datasets for Data Science Models, International Conference on Extending Database Technology (EDBT), 2025

4. Yangxin Fan, Raymond Wieser, Laura Bruckman, Roger French, Yinghui Wu. Parallel-friendly Spatio-Temporal Graph Learning for Photovoltaic Degradation Analysis at Scale, The 33rd ACM International Conference on Information and Knowledge Management (CIKM), 2024

5. Yangxin Fan, Xuanji Yu, Raymond Wieser, David Meakin, Avishai Shaton, Jean-Nicolas Jaubert, Robert Flottemesch, Michael Howell, Jennifer Braid, Laura Bruckman, Roger French, Yinghui Wu. Spatio-Temporal Denoising Autoencoder with Data Augmentation for Photovoltaic Timeseries Data Imputation, ACM International Conference on Management of Data (SIGMOD), 2023

AI for Science / Computational Social Science

Yangxin Fan, Raymond Wieser, Laura Bruckman, Yinghui Wu, Roger French. Parallelizable Spatio-Temporal Graph Learning for Photovoltaic Degradation Analysis, The 53rd IEEE Photovoltaic Specialists Conference (PVSC), 2025

2. Yangxin Fan, Raymond Wieser, Xuanji Yu, Yinghui Wu, Laura Bruckman, and Roger French. Using Spatio-Temporal Graph Neural Networks to Estimate Fleet-wide Photovoltaic Performance Degradation Patterns. PLOS ONE, 2024

3. Raymond Wieser, Yangxin Fan, Xuanji Yu, Jennifer Braid, Avishai Shaton, Adam Hoffman, Ben Spurgeon, Daniel Gibbons, Laura S Bruckman, Yinghui Wu, Roger H French. Large Scale, Data Driven, Digital Twin Models: Outlier Detection and Imputation, The 52nd IEEE Photovoltaic Specialists Conference (PVSC), 2024

4. Yangxin Fan, Raymond Wieser, Xuanji Yu, Jennifer Braid, Avishai Shaton, Adam Hoffman, Thevenard Dider, Ben Spurgeon, Daniel Gobbions, Laura Bruckman, Yinghui Wu, Roger French. Using Neural Network Decomposition to Estimate Field Photovoltaic Performance Loss Rate, The 50th IEEE Photovoltaic Specialists Conference (PVSC), 2023

5. Raymond Wieser, Yangxin Fan, Xuanji Yu, Jennifer Braid, Avishai Shaton, Adam Hoffman, Thevenard Dider, Ben Spurgeon, Daniel Gobbions, Laura Bruckman, Yinghui Wu, Roger French. Time-Series Imputation Using Graph Neural Networks and Denoising Autoencoders, The 50th IEEE Photovoltaic Specialists Conference (PVSC), 2023

6. William Oltjen, Yangxin Fan, Jiqi Liu, Liangyi Huang, Mingjie Li, Hubert Seigneur, Xusheng Xiao, Kristopher Davis, Laura Bruckman, Yinghui Wu, Roger French. FAIRification, Quality Assessment, and Missingness Pattern Discovery for Spatiotemporal Photovoltaic Data, The 49th IEEE Photovoltaic Specialists Conference (PVSC), 2022

7. Yangxin Fan, Hanjia Lyu, Jin Xiao, Jiebo Luo. Social Disparities in Oral Health in America amid the COVID-19 Pandemic, Quintessence International, 2022

8. Hanjia Lyu, Yangxin Fan, Ziyu Xiong, Mayya Komisarchik, Jiebo Luo. Understanding Public Opinion towards #StopAsianHate Movement Twitter #StopAsianHate movement and the Relation with Racially Motivated Hate Crimes in the US, IEEE Transactions on Computational Social Systems, 2021

Open-source Projects

1. HASolGNN

Introduction: a RAG-enhanced novel hierarchical Graph Neural Neural Networks + LLMs for molecular solubility prediction.

Detail: https://github.com/Yangxin666/HASolGNN

2. SPGC

Introduction: a novel structural-preserving graph compression supporting inference on billion-scale graphs while preserving accuracy.

Detail: https://github.com/Yangxin666/SPGC

3. ST-GTrend

Introduction: a Spatio-Temporal GNNs for trend profiling with model, data, pipeline parallelism leveraging CUDA-based multi-GPU training.

Detail: https://github.com/Yangxin666/ST-GTrend.

4. ST-GAE

Introduction: an open-source PyPi library for time series anomaly detection, imputation, and prediction.

Detail: https://pypi.org/project/PVplr-stGNN/

5. Fraud detection models and trust level validation in Mobile Money Transactions (MMT)

Introduction: To develop a service module train a series of fraud detection classifiers and choose top k best models and a client module which can validate the functionality of selected models and assign trust levels for mobile money transaction fraud detection.

Detail: https://github.com/Yangxin666/Fraud-detection-models-and-trust-level-validation-in-MMT

Architecture diagram

6. Predict Clinical Insomnia Among Cancer Survivors using YOCAS RCT data

Goal: To develop Machine Learning models to predict ISI (Insomnia Severity Index), analyze the patient-symptom bipartite network, and deliver clinically meaningful analysis.

Detail: https://github.com/Yangxin666/Predict-Clinical-Insomnia-Among-Cancer-Survivors-Using-Machine-Learning-Approaches-

Get in touch at

yxf451@case.edu

Page updated

Google Sites

Report abuse