Zhimeng Guo

Brief Bio

I am a graduate student at Penn State, specializing in the development of reliable and controllable Large Language Models. My research addresses fundamental challenges in AI alignment and verification through two primary streams: (1) advancing reasoning and safety alignment mechanisms, including post-training techniques and watermarking approaches, and (2) developing frameworks for interactive learning that enable models to engage in open-world problem solving and long-horizon planning.

2021 - Present: Graduate student at Penn State, advised by Prof. Minhao Cheng.
2017 - 2021: B.Sc. at UESTC, advised by Prof. Lianli Gao and Prof. Linyuan Lv.

Selected Publications

Jailbreak Open-Sourced Large Language Models via Enforced Decoding
Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu, Bochuan Cao, Lu Lin, Jinyuan Jia, Jinghui Chen, and Dinghao Wu. ACL, 2024.
[bib] [paper]

    @inproceedings{zhang2024jailbreak,
      title={Jailbreak open-sourced large language models via enforced decoding},
      author={Zhang, Hangfan and Guo, Zhimeng and Zhu, Huaisheng and Cao, Bochuan and Lin, Lu and Jia, Jinyuan and Chen, Jinghui and Wu, Dinghao},
      booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
      pages={5475--5493},
      year={2024}
    }

Addressing shortcomings in fair graph learning datasets: Towards a new benchmark
Xiaowei Qian*, Zhimeng Guo*, Jialiang Li, Haitao Mao, Bingheng Li, Suhang Wang, Yao Ma. KDD, 2024.
[bib] [paper]

      @inproceedings{qian2024addressing,
        title={Addressing shortcomings in fair graph learning datasets: Towards a new benchmark},
        author={Qian, Xiaowei and Guo, Zhimeng and Li, Jialiang and Mao, Haitao and Li, Bingheng and Wang, Suhang and Ma, Yao},
        booktitle={Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
        pages={5602--5612},
        year={2024}
      }

Towards Fair Graph Neural Networks via Graph Counterfactual.
Zhimeng Guo, Jialiang Li, Teng Xiao, Yao Ma, and Suhang Wang. CIKM, 2023.
[bib] [paper] [code]

@article{guo2023towards,
  title={Towards Fair Graph Neural Networks via Graph Counterfactual},
  author={Guo, Zhimeng and Li, Jialiang and Xiao, Teng and Ma, Yao and Wang, Suhang},
  journal={arXiv preprint arXiv:2307.04937},
  year={2023}
}

Efficient Contrastive Learning for Fast and Accurate Inference on Graphs.
Teng Xiao, Huaisheng Zhu, Zhiwei Zhang, Zhimeng Guo, Charu C Aggarwal, Suhang Wang, Vasant G Honavar. ICML, 2024.
[bib] [paper] [code]

    @inproceedings{xiao2024efficient,
      title={Efficient contrastive learning for fast and accurate inference on graphs},
      author={Xiao, Teng and Zhu, Huaisheng and Zhang, Zhiwei and Guo, Zhimeng and Aggarwal, Charu C and Wang, Suhang and Honavar, Vasant G},
      booktitle={Forty-first International Conference on Machine Learning},
      year={2024}
    }

Counterfactual Learning on Graphs: A Survey.
Zhimeng Guo, Teng Xiao, Charu Aggarwal, Hui Liu, and Suhang Wang. arXiv, 2023.
[bib] [paper] [code]

@misc{guo2023counterfactual,
  title={Counterfactual Learning on Graphs: A Survey}, 
  author={Zhimeng Guo and Teng Xiao and Charu Aggarwal and Hui Liu and Suhang Wang},
  year={2023},
  eprint={2304.01391},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}

Fairness-aware Message Passing for Graph Neural Networks.
Huaisheng Zhu, Guoji Fu, Zhimeng Guo, Zhiwei Zhang, Teng Xiao, and Suhang Wang. arXiv, 2023.
[bib] [paper]

@article{zhu2023fairnessaware,
  author = {Zhu, Huaisheng and Fu, Guoji and Guo, Zhimeng and Zhang, Zhiwei and Xiao, Teng and Wang, Suhang},
  journal = {arXiv},
  year = {2023},
  title = {Fairness-aware Message Passing for Graph Neural Networks},
  volume = {abs/2306.11132},
}

Decoupled Self-supervised Learning for Graphs.
Teng Xiao, Zhengyu Chen, Zhimeng Guo, Zeyang Zhuang, and Suhang Wang. NeurIPS, 2022.
[bib] [paper]

@inproceedings{xiao2022decoupled,
  author = {Xiao, Teng and Chen, Zhengyu and Guo, Zhimeng and Zhuang, Zeyang and Wang, Suhang},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  pages = {620--634},
  title = {Decoupled Self-supervised Learning for Graphs},
  volume = {35},
}

Label-Wise Graph Convolutional Network for Heterophilic Graphs.
Enyan Dai, Shijie Zhou, Zhimeng Guo, and Suhang Wang. LoG, 2022.
[bib] [paper] [code]

@article{dai2022comprehensive,
  title={A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability},
  author={Dai, Enyan and Zhao, Tianxiang and Zhu, Huaisheng and Xu, Junjie and Guo, Zhimeng and Liu, Hui and Tang, Jiliang and Wang, Suhang},
  journal={arXiv preprint arXiv:2204.08570},
  year={2022}
}

Link Prediction on Heterophilic Graphs via Disentangled Representation Learning.
Shijie Zhou, Zhimeng Guo, Charu Aggarwal, Xiang Zhang, and Suhang Wang. arXiv, 2022.
[bib] [paper] [code]

@article{zhou2022link,
  author = {Zhou, Shijie and Guo, Zhimeng and Aggarwal, C. and Zhang, Xiang and Wang, Suhang},
  journal = {arXiv},
  year = {2022},
  title = {Link Prediction on Heterophilic Graphs via Disentangled Representation Learning},
  volume = {abs/2208.01820},
}

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability.
Enyan Dai, Tianxiang Zhao, Huaisheng Zhu, Junjie Xu, Zhimeng Guo, Hui Liu, Jiliang Tang, and Suhang Wang. arXiv, 2022.
[bib] [paper] [code]

@article{dai2022a,
  author = {Dai, Enyan and Zhao, Tianxiang and Zhu, Huaisheng and Xu, Junjie and Guo, Zhimeng and Liu, Hui and Tang, Jiliang and Wang, Suhang},
  journal = {arXiv},
  year = {2022},
  title = {A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability},
  volume = {abs/2204.08570},
}

Teaching

IST 597 Data Science for Researchers and Scholars, Fall 2023.
DS 330 Visual Analytics, Spring 2024.

Awards / Acknowledgements / Services

Reviewer and subreviewer for AISTATS, NeurIPS, ICLR, SIGIR, IJCAI.
Outstanding Undergraduate Thesis Award.
Ranked 46/4103 in IEEEXtreme 24-Hour Programming Competition.
Meritorious Winner in 2019 MCM/ICM Mathematical Contest in Modeling.

Last update on Dec 6th, 2024.