🎓 About Me

🏫 I am currently a fifth-year Ph.D. student in the Department of Electrical and Computer Engineering at the University of Virginia, where I am advised by Prof. Jundong Li. Before joining UVA, I earned my B.E. in Electronic Engineering from Tsinghua University in 2020, where my diploma thesis was advised by Prof. Ji Wu.

📝 My research focuses on Adaptive AI and its applications in Biomedical & Health Informatics, while ensuring interpretability, efficiency, and robustness of developed algorithms and systems.

🤝 Looking for collaborations to work on impactful projects!

💼 I am actively seeking faculty positions! I would greatly appreciate it if you share any opportunities. Thank you!

🔍 Research Interests

My research aims to tackle real-world challenges in Adaptive, Generalizable, and Trustworthy AI, focusing on these topics:

• Adaptation/Generalization to New Tasks/Distributions: I develop theoretically grounded machine learning algorithms that enable generalization across diverse tasks and data distributions, focusing on invariance regularization and distribution-aware optimization to support generalization with theoretical guarantees.
  • TMLR 2025: Generative Risk Minimization for Out-of-Distribution Generalization on Graphs [PDF]
    Song Wang, Zhen Tan, Yaochen Zhu, Chuxu Zhang, Jundong Li.
  • ICDM 2024: Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization [PDF]
    Song Wang, Xiaodong Yang, Rashidul Islam, Huiyuan Chen, Minghua Xu, Jundong Li, Yiwei Cai.
• Generalization with Data-Efficiency: My work spans few-shot learning, in-context learning, and transfer learning, to minimize the requirement of supervision for adaptation.
  • ICML 2025: MAPLE: Many-Shot Adaptive Pseudo-Labeling In-Context Learning [PDF]
    Zihan Chen*, Song Wang*, Zhen Tan, Jundong Li, Cong Shen.
  • ICLR 2025: Reasoning of Large Language Models over Knowledge Graphs with Super-Relations [PDF]
    Song Wang, Junhong Lin, Xiaojie Guo, Julian Shun, Jundong Li, Yada Zhu.
  • NeurIPS 2024: Mixture of Demonstrations for In-Context Learning [PDF]
    Song Wang*, Zihan Chen*, Chengshuai Shi, Cong Shen, Jundong Li.
• Reliable Generalization: My research investigates the theoretical and empirical foundations of model robustness in the presence of noisy data, resource constraints, and spurious correlations. I design algorithms that enhance stability, fairness, and safety in generalization, especially for real-world deployment scenarios.
  • NeurIPS SoLaR 2025 Spotlight: On Demonstration Selection for Improving Fairness in Language Models [PDF]
    Song Wang, Peng Wang, Yushun Dong, Tong Zhou, Lu Cheng, Yangfeng Ji, Jundong Li.
  • EMNLP 2023: Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance [PDF]
    Song Wang, Zhen Tan, Ruocheng Guo, Jundong Li.
• Generalization for Biomedical & Health Informatics: I study how generalization theory can be extended to interdisciplinary domains such as biomedical informatics, healthcare, and particle physics. I develop methods that bridge theoretical rigor and scientific impact with guarantees in the presence of distribution shift.
  • AAAI 2025 Oral: BrainMAP: Learning Multiple Activation Pathways in Brain Networks [PDF]
    Song Wang*, Zhenyu Lei*, Zhen Tan, Jiaqi Ding, Xinyu Zhao, Yushun Dong, Guorong Wu, Tianlong Chen, Chen Chen, Aiying Zhang, Jundong Li.
  • BioArxiv 2025: A Natural Language Processing-Based Approach for Early Detection of Heart Failure Onset using Electronic Health Records [PDF]
    Yuxi Liu, Zhen Tan, Zhenhao Zhang, Song Wang, Jingchuan Guo, Huan Liu, Tianlong Chen, Jiang Bian.
  • Arxiv 2025: Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis [PDF]
    Shuang Zhou, Jiashuo Wang, Zidu Xu, Song Wang, David Brauer, Lindsay Welton, Jacob Cogan, Yuen-Hei Chung, Lei Tian, Zaifu Zhan, Yu Hou, Mingquan Lin, Genevieve B. Melton, Rui Zhang.

🔥 News and Updates

• 2025.05:  🎉 One paper Fairness-Aware Graph Learning: A Benchmark is accepted at KDD 2025 Dataset Track! See you in Toronto (definitely)!
• 2025.05:  🎉 One co-first paper MAPLE: Many-Shot Adaptive Pseudo-Labeling In-Context Learning is accepted at ICML 2025! See you in Vancouver! Yes, we named it MAPLE to match the conference location.
• 2025.01:  🎉 Three papers (one Spotlight first-author, one first-author) are accepted at ICLR 2025! See you (maybe) in Singapore!
• 2025.01:  🎉 Our paper (first-author), Generative Risk Minimization for Out-of-Distribution Generalization on Graphs, is accepted at TMLR!
• 2024.12:  🎉 Four papers (one first-author Oral, one Oral) are accepted at AAAI 2025! See you in Philadelphia!
• 2024.10:  🎉 Two papers are accepted at EMNLP 2024 Main! See you in Miami!
• 2024.10:  🎉 Two papers on Fairness in Large Language Models are accepted at NeurIPS SoLaR (One Spotlight)!
• 2024.10:  🎉 Our paper, “Mixture of Demonstrations for In-Context Learning,” is accepted at NeurIPS 2024! See you in Vancouver!
• 2024.10:  🎉 One paper is accepted at IEEE BigData 2024!
• 2024.10:  🎉 One paper is accepted at WSDM 2024!
• 2024.10:  🎉 Our paper, “Federated Graph Learning with Graphless Clients,” is accepted at TMLR!
• 2024.09:  🎉 Published “Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization” at ICDM 2024.
• 2024.09:  🎉 Our survey “Knowledge Editing for Large Language Models: A Survey,” is accepted at ACM Computing Surveys.
• 2024.07:  🎉 Our paper, “Understanding and Modeling Job Marketplace with Pretrained Language Models,” is accepted at CIKM 2024 Applied Research Track!
• 2024.05:  🎉 Two papers are accepted at ACL 2024 Findings!
• 2024.02:  🎉 Our paper, “Interpreting Pretrained Language Models via Concept Bottlenecks”, is accepted at PAKDD 2024 with Best Paper Award!

📖 Education

• University of Virginia: Ph.D. in Electrical and Computer Engineering (2020 – Present)
• Tsinghua University: B.E. in Electronic Engineering (2016 – 2020)

💼 Professional Experience

• Meta: Research Scientist Intern (Sep 2024 – Dec 2024)
  Bellevue, Washington · On-site

• Massachusetts Institute of Technology: Visiting Ph.D. Student (Jun 2024 – Aug 2024)
  Cambridge, Massachusetts · On-site

• Visa: Research Intern (May 2023 – Aug 2023)
  Atlanta, Georgia · On-site

📜 Selected Publications

2025

• KDD Dataset Track: Fairness-Aware Graph Learning: A Benchmark
  Yushun Dong, Song Wang, Zhenyu Lei, Zaiyi Zheng, Jing Ma, Chen Chen, Jundong Li.

• ICML: MAPLE: Many-Shot Adaptive Pseudo-Labeling In-Context Learning [PDF]
  Zihan Chen*, Song Wang*, Zhen Tan, Jundong Li, Cong Shen.

• ICLR Spotlight: CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models [PDF] [GitHub]
  Song Wang*, Peng Wang*, Tong Zhou, Yushun Dong, Zhen Tan, Jundong Li.

• ICLR: Reasoning of Large Language Models over Knowledge Graphs with Super-Relations [PDF]
  Song Wang, Junhong Lin, Xiaojie Guo, Julian Shun, Jundong Li, Yada Zhu.

• ICLR: Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective [PDF]
  Yushun Dong, Yinhan He, Patrick Soga, Song Wang, Jundong Li.

• Arxiv: A Survey of Deep Graph Learning under Distribution Shifts: From Graph Out-of-Distribution Generalization to Adaptation [PDF]
  Kexin Zhang, Shuhan Liu, Song Wang, Weili Shi, Chen Chen, Pan Li, Sheng Li, Jundong Li, Kaize Ding.

• TMLR: Generative Risk Minimization for Out-of-Distribution Generalization on Graphs [PDF]
  Song Wang, Zhen Tan, Yaochen Zhu, Chuxu Zhang, Jundong Li.

• AAAI Oral: BrainMAP: Learning Multiple Activation Pathways in Brain Networks [PDF]
  Song Wang*, Zhenyu Lei*, Zhen Tan, Jiaqi Ding, Xinyu Zhao, Yushun Dong, Guorong Wu, Tianlong Chen, Chen Chen, Aiying Zhang, Jundong Li.

• AAAI Oral: Tuning-Free Accountable Intervention for LLM Deployment - A Metacognitive Approach [PDF]
  Zhen Tan, Jie Peng, Song Wang, Lijie Hu, Tianlong Chen, Huan Liu.

• AAAI: Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective [PDF]
  Yiming Xu, Zhen Peng, Bin Shi, Xu Hua, Bo Dong, Song Wang, Chen Chen.

• AAAI: Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning [PDF]
  Xingbo Fu, Zihan Chen, Yinhan He, Song Wang, Binchi Zhang, Chen Chen, Jundong Li.

• TKDE (under revision): Safety in Graph Machine Learning: Threats and Safeguards [PDF]
  Song Wang, Yushun Dong, Binchi Zhang, Zihan Chen, Xingbo Fu, Yinhan He, Cong Shen, Chuxu Zhang, Nitesh V. Chawla, Jundong Li.

2024

• NeurIPS: Mixture of Demonstrations for In-Context Learning [PDF]
  Song Wang*, Zihan Chen*, Chengshuai Shi, Cong Shen, Jundong Li.

• ACM Computing Surveys: Knowledge Editing for Large Language Models: A Survey [PDF]
  Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, Jundong Li.

• ICDM: Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization [PDF]
  Song Wang, Xiaodong Yang, Rashidul Islam, Huiyuan Chen, Minghua Xu, Jundong Li, Yiwei Cai.

• NeurIPS SoLaR Spotlight: On Demonstration Selection for Improving Fairness in Language Models [PDF]
  Song Wang, Peng Wang, Yushun Dong, Tong Zhou, Lu Cheng, Yangfeng Ji, Jundong Li.

• ACL Findings: FastGAS: Fast Graph-based Annotation Selection for In-Context Learning [PDF]
  Zihan Chen, Song Wang, Cong Shen, Jundong Li.

• ACL Findings: Knowledge Graph-Enhanced Large Language Models via Path Selection [PDF]
  Haochen Liu, Song Wang, Yaochen Zhu, Yushun Dong, Jundong Li.

• EMNLP Main: Large Language Models for Data Annotation: A Survey [PDF]
  Zhen Tan*, Dawei Li*, Song Wang*, Alimohammad Beigi, Bohan Jiang, Amrita Bhattacharjee, Mansooreh Karami, Jundong Li, Lu Cheng, Huan Liu.

• EMNLP Main: Glue Pizza and Eat Rocks - Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [PDF]
  Zhen Tan, Chengshuai Zhao, Raha Moraffah, Yifan Li, Song Wang, Jundong Li, Tianlong Chen, Huan Liu.

• IEEE BigData: KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models [PDF]
  Zaiyi Zheng, Yushun Dong, Song Wang, Haochen Liu, Qi Wang, Jundong Li.

• WSDM: Demystify Epidemic Containment in Directed Networks: Theory and Algorithms [PDF]
  Yinhan He, Chen Chen, Song Wang, Guanghui Min, Jundong Li.

• CIKM: Understanding and Modeling Job Marketplace with Pretrained Language Models
  Yaochen Zhu, Liang Wu, Binchi Zhang, Song Wang, Qi Guo, Liangjie Hong, Luke Simon, Jundong Li.

• PAKDD Best Paper: Interpreting Pretrained Language Models via Concept Bottlenecks [PDF]
  Zhen Tan, Lu Cheng, Song Wang, Yuan Bo, Jundong Li, Huan Liu.

2023

• TKDD: Learning Hierarchical Task Structures for Few-shot Graph Classification [PDF]
  Song Wang, Yushun Dong, Xiao Huang, Chen Chen, Jundong Li.

• EMNLP: Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance [PDF]
  Song Wang, Zhen Tan, Ruocheng Guo, Jundong Li.

• ECAI: Fair Few-shot Learning with Auxiliary Sets [PDF]
  Song Wang, Jing Ma, Lu Cheng, Jundong Li.

• SIGKDD: Federated Few-shot Learning [PDF]
  Song Wang, Xingbo Fu, Chen Chen, Jundong Li.

• SIGKDD: Contrastive Meta-Learning for Few-shot Node Classification [PDF]
  Song Wang*, Zhen Tan*, Huan Liu, Jundong Li.

• TKDE: Fairness in Graph Mining: A Survey [PDF]
  Yushun Dong, Jing Ma, Song Wang, Chen Chen, Jundong Li.

• AAAI: Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
  Yushun Dong, Song Wang, Jing Ma, Ninghao Liu, Jundong Li.

• WSDM: Few-shot Node Classification with Extremely Weak Supervision [PDF]
  Song Wang, Yushun Dong, Kaize Ding, Chen Chen, Jundong Li.

2022

• LoG (Spotlight): Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification [PDF]
  Zhen Tan*, Song Wang*, Kaize Ding*, Jundong Li, Huan Liu.

• NeurIPS: Graph Few-shot Learning with Task-specific Structures [PDF]
  Song Wang, Chen Chen, Jundong Li.

• SIGKDD: Task-Adaptive Few-shot Node Classification [PDF]
  Song Wang, Kaize Ding, Chuxu Zhang, Chen Chen, Jundong Li.

• IJCAI: FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs [PDF]
  Song Wang, Yushun Dong, Xiao Huang, Chen Chen, Jundong Li.

• SIGIR: Recognizing Medical Search Query Intent by Few-shot Learning [PDF]
  Yaqing Wang*, Song Wang*, Yanyan Li, Dejing Dou.

Full Publication List (Google Scholar)

💁 Service and Volunteering

• Conference Reviewer: NeurIPS, ICML, ACL, SIGKDD, NAACL, EMNLP.
• Mentorship: Directly supervised 6 undergraduate and graduate students, many of whom have published at top venues like NAACL and NeurIPS.

🐱 Hobbies and Interests

Beyond research, I enjoy:
🏊‍🚴🏃 Triathlon (training)
⚾ Baseball (playing)
🌟 Exploration Applications of AI for social good (e.g., personalized chatbot on social media)

Feel free to contact me for collaborations, research discussions, or just to connect!

🌍 Visits