Yue Dai 「戴岳」

Yue Dai 「戴岳」

Assistant Professor in Illinois Tech

Welcome to Yue Dai’s Homepage

I am a tenure-track assistant professor in the Department of Computer Science at Illinois Institute of Technology (Illinois Tech). I earned my Ph.D. in Computer Science from the University of Pittsburgh under the guidance of Dr. Youtao Zhang and Dr. Xulong Tang. I received my M.S. in Telecommunications from the University of Maryland and my B.E. in Electrical Engineering from Beihang University, China.

My research focuses on efficient and trustworthy computing systems for advanced graph learning and machine learning applications. I accelerate Graph Neural Networks across heterogeneous hardware—from edge devices to multi-GPU clusters—while safeguarding them against adaptive adversarial attacks. Looking ahead, I aim to design scalable infrastructure for complex graph learning applications, including real-time dynamic graph learning and low-latency agent-based systems (e.g., Efficient Temporal Graph Neural Networks, Graph Matching, Graph-based AI Agents, etc). In parallel, I am developing full-stack software–hardware co-designs that enable efficient solutions for graph-aware and general AI applications (e.g., Efficient GraphRAG, LLM Serving, etc.). I am also investigating adversarial robustness and system security of deep graph learning models, including adversarial attacks and defenses on Temporal Graph Neural Networks.

🌟 I am recruiting self-motivated Ph.D. students to join my group in Spring/Fall 2026 who have interests in efficient graph deep learning, efficient LLM serving, or security in deep graph learning.

CV/Email/Google Scholar/Linkedin

News

[05/2025] One paper is accepted by ICML2025. Thanks to all the collaborators!
[01/2025] One paper is accepted by ISCA2025. Thanks to all the collaborators!
[01/2025] One paper is accepted by ASPLOS2025. Thanks to all the collaborators!
[01/2025] One paper is accepted by ICLR2025. Thanks to all the collaborators!
[08/2023] One paper is accepted by ICCD2023. Thanks to all the collaborators!
[01/2023] One paper is accepted by ICLR2023 (spotlight). Thanks to all the collaborators!
[10/2022] One paper is accepted by HPCA2023. Thanks to all the collaborators!
[08/2022] One paper is accepted by ArgMining2022 (best paper). Thanks to all the collaborators!
[06/2022] One paper is accepted by CCF Transactions on High Performance Computing. Thanks to all the collaborators!

Publications

* co‑first author

  • Yue Dai, Liang Liu, Xulong Tang, Youtao Zhang, Jun Yang. 2025. MemStranding: Adversarial attacks on temporal graph neural networks. The Thirteenth International Conference on Learning Representations (ICML’2025)

  • Yue Dai, Xulong Tang, Youtao Zhang. 2025. Cascade: A Dependency‑Aware Efficient Training Framework for Temporal Graph Neural Network. 2025 ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS’2025).

  • Li, Yingheng, Yue Dai, Aditya Pawar, Rongchao Dong, Jun Yang, Youtao Zhang, and Xulong Tang. 2025. Using Reinforcement Learning to Guide Graph State Generation for Photonic Quantum Computers. The 52nd International Symposium on Computer Architecture (ISCA’2025).

  • Sheng Li, Qitao Tan, Yue Dai, Zhenglun Kong, Tianyu Wang, Jun Liu, Ao Li, Ninghao Liu, Yufei Ding, Xulong Tang, Geng Yuan. 2025. Mutual Effort for Efficiency: A Similarity‑based Token Pruning for Vision Transformers in Self‑Supervised Learning. The Thirteenth International Conference on Learning Representations (ICLR’2025).

  • Yue Dai, Youtao Zhang, Xulong Tang. 2023. CEGMA: Coordinated elastic graph matching acceleration for graph matching networks. 2023 IEEE International Symposium on High‑Performance Computer Architecture (HPCA’2023).

  • Yue Dai, Xulong Tang, Youtao Zhang. 2023. FlexGM: An Adaptive Runtime System to Accelerate Graph Matching Networks on GPUs. 2023 IEEE 41st International Conference on Computer Design (ICCD’2023).

  • Sheng Li*, Geng Yuan*, Yue Dai*, Youtao Zhang, Yanzhi Wang, Xulong Tang. 2023. Smartfrz: An efficient training framework using attention‑based layer freezing. The 11th International Conference on Learning Representations (ICLR’2023).

  • Yue Dai, Xulong Tang, Youtao Zhang. 2022. An efficient segmented quantization for graph neural networks. CCF Transactions on High Performance Computing (THPC’2023), 4(4), 461‑473.

  • Zhexiong Liu*, Meiqi Guo*, Yue Dai*, Diane Litman. 2022. ImageArg: A multi‑modal tweet dataset for image persuasiveness mining. Proceedings of the 9th Workshop on Argument Mining at International Conference on Computational Linguistics (COLING’2022).

  • Sheng Li, Geng Yuan, Yawen Wu, Yue Dai, Chao Wu, Alex K Jones, Jingtong Hu, Yanzhi Wang, Xulong Tang. 2024. EdgeOL: Efficient in‑situ Online Learning on Edge Devices. arXiv preprint arXiv:2401.16694.

  • Justin Brody, Samuel Barham, Yue Dai, Christopher Maxey, Donald Perlis, David Sekora, Jared Shamwell. 2016. Reasoning with grounded self‑symbols for human‑robot interaction. 2016 AAAI Fall Symposium Series.