Rao Yanghui

Associate Professor

Email: raoyangh@mail.sysu.edu.cn

教师简介: 

饶洋辉，副教授，博士生导师。2014年博士毕业于香港城市大学，师从李青教授。主持国家自然科学基金面上项目、青年科学基金项目，广东省自然科学基金面上项目，以及教育部专项等课题，入选“广东特支计划”科技创新青年拔尖人才，并参与多项国家自然科学基金-广东大数据科学中心联合基金重点支持项目和国家重点研发计划课题。研究成果发表在IEEE Transactions on Knowledge and Data Engineering、Transactions of the Association for Computational Linguistics、Computational Linguistics、Nature Communications、Bioinformatics、ACL、IJCAI、CIKM、ISWC、KDD、ECML、EMNLP、NAACL等期刊和会议上。曾获CCF B类会议DASFAA'17的最佳论文亚军奖。研究团队（代码集：https://github.com/YRaoGroup；专著：https://link.springer.com/book/10.1007/978-981-96-8853-1）招收博士、硕士和本科生，欢迎感兴趣的同学联系。

研究领域: 

  • 语言模型、知识图谱、主题建模、文本生成、情感分析

工作经历: 

  • 2014.9 - 至今，中山大学，移动信息工程学院、数据科学与计算机学院、计算机学院

科研项目: 

  1. 国家自然科学基金面上项目 (61972426, 62372483)，负责人。
  2. 国家自然科学基金青年科学基金项目 (61502545)，负责人。
  3. 广东省自然科学基金面上项目 (2020A1515010536)，负责人。
  4. 中山大学粤港澳发展研究院年度课题，负责人。
  5. 中山大学网络与信息技术中心预研究项目，负责人。

主要学术兼职: 

  • Associate Editor: Natural Language Processing Journal
  • Editorial Board: Information Processing & Management
  • Area Chair: ARR 2026, NAACL 2025, ACL & EMNLP 2024
  • PC Member & Reviewer: ICLR 2025-26, ICML 2025-26, KDD 2022-26, WWW 2024-25, AAAI 2019-25, IJCAI 2021-24, IEEE TPAMI & TKDE

代表性论著: 

期刊论文：

  • Hegang Chen, Yuyin Lu, Yifan Zhao, Zhiming Dai, Fu Lee Wang, Qing Li, Yanghui Rao*, Yue Li*, scE2TM improves single-cell embedding interpretability and reveals cellular perturbation signatures,  Nature Communications, 2026, accepted. [The preprint of this work was completed while Hegang Chen was a PhD student in his final year]
  • Bin Zhu, Yi Xie, Yanxia Feng, Fu Lee Wang, Haoran Xie, Yanghui Rao*, Causal adversarial training for improving language understanding and robustness, Computational Linguistics, 2026, accepted.
  • Jianxing Yu, Haowei Jiang, Huaijie Zhu, Wenqing Chen, Yanghui Rao, Qinliang Su, Jian Yin*, Accelerated optimization of large mixture-of-experts models by density-aware multi-stage learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026, 48(5): 5505-5519.
  • Yuyin Lu, Hegang Chen, Yanghui Rao*, Jianxing Yu, Wen Hua, Qing Li, An efficient fuzzy system for complex query answering on knowledge graphs, IEEE Transactions on Knowledge and Data Engineering, 2025, 37(9): 4962-4976.
  • 余建兴, 王世祺, 陈祺, 赖韩江, 饶洋辉, 苏勤亮, 印鉴*, 基于常识推理问答的多模态题文不符检测, 软件学报, 2025, 36(12): 5720-5738.
  • Ruihao Chen, Hegang Chen, Yuyin Lu, Yanghui Rao*, Chunjiang Zhu*, Supervised neural topic modeling with label alignment, Transactions of the Association for Computational Linguistics, 2025, 13: 249-263.
  • Yuyin Lu, Hegang Chen, Pengbo Mao, Yanghui Rao*, Haoran Xie, Fu Lee Wang, Qing Li, Self-supervised topic taxonomy discovery in the box embedding space, Transactions of the Association for Computational Linguistics, 2024, 12: 1401-1416.
  • Hegang Chen, Yuyin Lu, Yanghui Rao*, A self-training interpretable cell type annotation framework using specific marker gene, Bioinformatics, 2024, 40(10): btae569.
  • Hegang Chen, Yuyin Lu, Zhiming Dai, Yuedong Yang, Qing Li, Yanghui Rao*, Comprehensive single-cell RNA-seq analysis using deep interpretable generative modeling guided by biological hierarchy knowledge, Briefings in Bioinformatics, 2024, 25(4): bbae314.
  • Zhiqi Lei, Hai Liu, Jiaxing Yan, Yanghui Rao*, Qing Li, NMTF-LTM: Towards an alignment of semantics for lifelong topic modeling, IEEE Transactions on Knowledge and Data Engineering, 2023, 35(10): 10616-10632.
  • Yufu Chen, Zhiqi Lei, Yanghui Rao*, Haoran Xie, Fu Lee Wang, Jian Yin, Qing Li, Parallel non-negative matrix tri-factorization for text data co-clustering, IEEE Transactions on Knowledge and Data Engineering, 2023, 35(5): 5132-5146.
  • Hegang Chen, Yuyin Lu, Yuedong Yang, Yanghui Rao*, A drug combination prediction framework based on graph convolutional network and heterogeneous information, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2023, 20(3): 1917-1925.
  • Yufu Chen, Yanghui Rao*, Shurui Chen, Zhiqi Lei, Haoran Xie, Raymond Y. K. Lau, Jian Yin, Semi-supervised sentiment classification and emotion distribution learning across domains. ACM Transactions on Knowledge Discovery from Data, 2023, 17(5): 74:1-74:30.
  • Zusheng Zhang, Yanghui Rao*, Hanjiang Lai, Jiahai Wang, Jian Yin, TADC: A topic-aware dynamic convolutional neural network for aspect extraction, IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(8): 3912-3924.
  • 陈姝睿, 梁子然, 饶洋辉*, 细粒度语义知识图谱增强的中文OOV词嵌入学习, 计算机科学, 2023, 50(3): 72-82.
  • Lihui Lin, Yanghui Rao*, Haoran Xie, Raymond Y. K. Lau, Jian Yin, Fu Lee Wang, Qing Li, Copula guided parallel gibbs sampling for nonparametric and coherent topic discovery, IEEE Transactions on Knowledge and Data Engineering, 2022, 34(1): 219-235.

会议论文：

  • Yuyin Lu, Ziran Liang, Yanghui Rao*, Wenqi Fan, Fu Lee Wang, Qing Li, Double-calibration: Towards reliable LLMs via calibrating knowledge and reasoning confidence, IJCAI, 2026, accepted.
  • Yuyin Lu, Hegang Chen, Shanrui Xie, Yanghui Rao*, Haoran Xie, Fu Lee Wang, Qing Li, Existentially consistent skolemized reasoning for complex query answering on knowledge graphs, CIKM, 2026, accepted.
  • Bin Zhu, Yi Xie, Yanghui Rao*, Stopping and routing LLM judge panels, WISE, 2026, accepted.
  • Bin Zhu, Yi Xie, Yanghui Rao*, A finite-calibration regime map for LLM judge panels, WISE, 2026, accepted.
  • Fanjin Zhang, Yunhe Pang, Bo Chen, Zhiyu Shen, Yanghui Rao*, Evgeny Kharlamov, Jie Tang*, Cross-source reasoning-based correction for author name disambiguation, KDD, 2026, pp. 8489-8500. [This work was done when Yunhe Pang interned at Zhipu AI]
  • Zhiyu Shen, Jiyuan Liu, Yunhe Pang, Yanghui Rao*, Fu Lee Wang, Jianxing Yu, HopWeaver: Cross-document synthesis of high-quality and authentic multi-hop questions, ACL, 2026, pp. 28078-28109.
  • Zhiyu Shen, Ziming Wu*, Fuming Lai, Shaobing Lian, Yanghui Rao, MemBuilder: Reinforcing LLMs for long-term memory construction via attributed dense rewards, ACL, 2026, pp. 27868-27887. [This work was done when Zhiyu Shen interned at Tencent]
  • Zhiyu Shen, Yunhe Pang, Yanghui Rao*, Jianxing Yu, CoE: A clue of emotion framework for emotion recognition in conversations, ACL, 2025, pp. 23548-23563.
  • Yunhe Pang, Bo Chen, Fanjin Zhang*, Yanghui Rao, Evgeny Kharlamov, Jie Tang*, GuARD: Effective anomaly detection through a text-rich and graph-informed language model, KDD, 2025, pp. 2222-2233. [This work was done when Yunhe Pang interned at Zhipu AI]
  • Detian Zhang, Chengqiang Zhang, Yanghui Rao, Qing Li, Chunjiang Zhu*, Improved expressivity of hypergraph neural networks through high-dimensional generalized weisfeiler-leman algorithms, ICML, 2025.
  • Fan Li, Jianxing Yu*, Jielong Tang, Wenqing Chen, Hanjiang Lai, Yanghui Rao, Jian Yin, Answering complex geographic questions by adaptive reasoning with visual context and external commonsense knowledge, ACL, 2025, pp. 25498-25514.
  • Xingyu Liu, Yuyin Lu, Yanghui Rao*, Leveraging open path from pruned graph for link prediction on knowledge graphs, ISWC, 2025, pp. 556-574.
  • Jiyuan Liu, Jiaxing Yan, Chunjiang Zhu, Xingyu Liu, Qing Li, Yanghui Rao*, Neural topic modeling via contextual and graph information fusion, EMNLP, 2025, pp. 13259-13275.
  • Jiyuan Liu, Jielin Song, Yunhe Pang, Zhiyu Shen, Yanghui Rao*, CARE: A disagreement detection framework with concept alignment and reasoning enhancement, EMNLP, 2025, pp. 13276-13291.
  • Yufeng Zhang, Jianxing Yu*, Yanghui Rao, Libin Zheng, Qinliang Su, Huaijie Zhu, Jian Yin, Domain adaptation for subjective induction questions answering on products by adversarial disentangled learning, ACL, 2024, pp. 9074-9089.
  • Jiaxing Yan, Yuyin Lu, Hegang Chen, Jianxing Yu, Yanghui Rao*, Lifelong hierarchical topic modeling via nonparametric word embedding clustering, ECML, 2024, pp. 270-287.
  • Zhicheng Lin, Hegang Chen, Yuyin Lu, Yanghui Rao*, Hao Xu*, Hanjiang Lai, Hierarchical topic modeling via contrastive learning and hyperbolic embedding, COLING, 2024, pp. 8133-8143.
  • Jiyuan Liu, Hegang Chen, Chunjiang Zhu, Yanghui Rao*, Unsupervised hierarchical topic modeling via anchor word clustering and path guidance, EMNLP: Findings, 2024, pp. 7505-7517.
  • Ziran Liang, Yuyin Lu, Hegang Chen, Yanghui Rao*, Graph-based relation mining for context-free out-of-vocabulary word embedding learning, ACL, 2023, pp. 14133-14149.
  • Hegang Chen, Pengbo Mao, Yuyin Lu, Yanghui Rao*, Nonlinear structural equation model guided gaussian mixture hierarchical topic modeling, ACL, 2023, pp. 10377-10390.
  • Wangzhen Guo, Qinkang Gong, Yanghui Rao, Hanjiang Lai*, Counterfactual multihop QA: A cause-effect approach for reducing disconnected reasoning, ACL, 2023, pp. 4214-4226.
  • Bin Zhu, Yanghui Rao*, Exploring robust overfitting for pre-trained language models, ACL: Findings, 2023, pp. 5506-5522.
  • Yuyin Lu, Xin Cheng, Ziran Liang, Yanghui Rao*, Graph-based dynamic word embeddings, IJCAI, 2022, pp. 4280-4288.