Gangrong Jiang

Gangrong Jiang is currently a graduate student at USC. His interests lie in reasoning and natural language generation. Specifically, he has experience in text summarization, question answering in unstructured and semi-structured data, reinforcement learning, and knowledge graph reasoning. His current research focuses on label-efficient deep learning and interpretable AI.



Research Assistant | Advisor: Prof. Sean (Xiang) Ren

Los Angeles, CA


June 2020 - Aug. 2020

Software Engineer Intern

Mountain View, CA

Research Assistant | Advisor: Prof. Zhenglu Yang

Tianjin, China


  • Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning

    Gangrong Jiang*, Deren Lei*, Xiaotao Gu, Kexuan Sun, Yuning Mao, Xiang Ren (* equal contribution)

    The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020

        title = "Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning",
        author = "Lei, Deren  and
          Jiang, Gangrong  and
          Gu, Xiaotao  and
          Sun, Kexuan  and
          Mao, Yuning  and
          Ren, Xiang",
        booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
        month = nov,
        year = "2020",
        address = "Online",
        publisher = "Association for Computational Linguistics",
        url = "",
        doi = "10.18653/v1/2020.emnlp-main.688",
        pages = "8541--8547",
        abstract = "Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward signals offered by the KG during a traversal are often insufficient to guide a sophisticated walk-based reinforcement learning (RL) model. An alternate approach is to use traditional symbolic methods (e.g., rule induction), which achieve good performance but can be hard to generalize due to the limitation of symbolic representation. In this paper, we propose RuleGuider, which leverages high-quality rules generated by symbolic-based methods to provide reward supervision for walk-based agents. Experiments on benchmark datasets shows that RuleGuider clearly improves the performance of walk-based models without losing interpretability.",
  • Self-Supervised Relation Learning for Knowledge Graph Reasoning

    Gangrong Jiang*, Deren Lei*, Kexuan Sun, Xiang Ren (* equal contribution)

    In Submission

  • Learning to Reason in Round-based Games: Multi-task Sequence Generation for Purchasing Decision Making in First-person Shooters

    Gangrong Jiang*, Yilei Zeng*, Deren Lei*, Beichen Li*, Emilio Ferrara, Michael Zyda (* equal contribution)

    The 16th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-20), 2020

        title={Learning to Reason in Round-Based Games: Multi-Task Sequence Generation for Purchasing Decision Making in First-Person Shooters},
        abstractNote={<p class="abstract">Sequential reasoning is a complex human ability, with extensive previous research focusing on gaming AI in a single continuous game, round-based decision makings extending to a sequence of games remain less explored. Counter-Strike: Global Offensive (CS:GO), as a round-based game with abundant expert demonstrations, provides an excellent environment for multi-player round-based sequential reasoning. In this work, we propose a Sequence Reasoner with Round Attribute Encoder and Multi-Task Decoder to interpret the strategies behind the round-based purchasing decisions. We adopt few-shot learning to sample multiple rounds in a match, and modified model agnostic meta-learning algorithm Reptile for the meta-learning loop. We formulate each round as a multi-task sequence generation problem. Our state representations combine action encoder, team encoder, player features, round attribute encoder, and economy encoders to help our agent learn to reason under this specific multi-player round-based scenario. A complete ablation study and comparison with the greedy approach certify the effectiveness of our model. Our research will open doors for interpretable AI for understanding episodic and long-term purchasing strategies beyond the gaming community.</p>},
        journal={Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment},
        author={Zeng, Yilei and Lei, Deren and Li, Beichen and Jiang, Gangrong and Ferrara, Emilio and Zyda, Michael},
  • Neural Module Teacher: Learning to Answer Questions with Compositional Explanation

    Qinyuan Ye, Xiao Huang, Yujia Qin, Gangrong Jiang, Ziqi Wang, Xiang Ren

    In Submission

  • TSAS: A Transformer-based Model for Sentiment-Aware Abstractive Summarization

    Gangrong Jiang*, Ziming Chi*, Zhenglu Yang (* equal contribution)

    Technical Report, 2018

Personal Interest

  • Sports: badminton, tennis
  • Traveling
  • Gaming: League of Legends
  • Rap