👋 About Me

I am an Assistant Professor at the Intelligent Game and Decision Lab, Academy of Military Sciences, Beijing. From 2015 to 2024, I earned my bachelor’s and doctoral degrees in Management Science and Engineering (管理科学与工程) from the College of Systems Engineering, National University of Defense Technology, under the supervision of Prof. Zhong Liu (刘忠) and Prof. Changjun Fan (范长俊). I was also a visiting Ph.D. student at Tsinghua University from 2022 to 2024, advised by Prof. Peng Cui (崔鹏).

I have published over 20 papers in top-tier journals and conferences, including IEEE TPAMI, IEEE TKDE, The Innovation, NeurIPS, ICML, KDD, WWW, ICDE, CVPR, and AAAI. My primary research interests include: 1) Logical Reasoning — encompassing both rule learning on knowledge graphs and logical reasoning with LLMs; 2) OOD Generalization — with a focus on higher-order and complex data such as graphs, heterogeneous information networks, and dynamic systems; 3) Database Management — focusing on the representation, processing, and querying of tables; and 4) Foundation Models — with particular emphasis on prior-fitted networks and their applications in AI4S domains.

I am open to research discussions and collaboration opportunities. Please feel free to contact me at liushixuan@nudt.edu.cn or szftandy@hotmail.com.

🔥 News

• [2026.05] 🎉🎉 One paper is accepted by KDD 2026.
• [2026.05] 🎉🎉 Two papers are accepted by ICML 2026.
• [2026.02] 🎉🎉 One paper is accepted by ICDE 2026.
• [2026.02] 🎉🎉 One paper is accepted by CVPR 2026.
• [2026.01] 🎉🎉 One paper is accepted by WWW 2026.
• [2025.11] 🎉🎉 Two papers are accepted by AAAI 2026.
• [2025.09] 🎉🎉 Two papers are accepted by NeurIPS 2025, including one Highlight (top 3.17%) paper.

📝 Publications

* Equal Contribution, † Corresponding Author

• Inductive Meta-Path Learning for Schema-Complex Heterogeneous Information Networks [IEEE TPAMI]
  Shixuan Liu, Changjun Fan†, Kewei Cheng, Yunfei Wang, Peng Cui, Yizhou Sun, Zhong Liu†
• Environment Inference for Learning Generalizable Dynamical System [NeurIPS 2025, Highlight]
  Shixuan Liu, Yue He†, Haotian Wang, Wenjing Yang, Yunfei Wang, Peng Cui†, Zhong Liu
• Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models [KDD 2026]
  Haoxiang Cheng, Yunfei Wang, Chao Chen, Kewei Cheng, Zhipeng Lin, Haoxuan Li, Changjun Fan, Shixuan Liu†
• LogicSAGE: Neuro-Symbolic Reasoning with Socratic-Guided Enhancement [ICML 2026]
  Jinlong Tian, Jiang Yu, Kewei Cheng, Fengxiang Cheng, Yue He, Yunfei Wang, Haotian Wang, Haoxuan Li, Wenjing Yang, Shixuan Liu†
• Invariant Learning on Heterogeneous Graphs via Subgraph Environment Inference [WWW 2026]
  Yanghui Fu, Yunfei Wang, Hao Zou, Yue He, Haotian Wang, Qing Cheng, Guangquan Cheng, Shixuan Liu†
• L³C: Leaf-Centric Continuous Codes for Natural Language-Driven Table Discovery [ICDE 2026]
  Qiyuan Zhang, Ruochun Jin, Jixin Zhang, Yuhua Tang, Xiang Zhao, Shixuan Liu†
• Graph-Attention-Based Causal Discovery With Trust Region-Navigated Clipping Policy Optimization [IEEE TCYB]
  Shixuan Liu, Yanghe Feng†, Keyu Wu, Guangquan Cheng, Jincai Huang, Zhong Liu
• Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift [In Revision, IEEE TPAMI]
  Shixuan Liu, Yue He, Yunfei Wang, Hao Zou, Haoxiang Cheng, Wenjing Yang†, Peng Cui†, Zhong Liu
• EvoPath: Evolutionary meta-path discovery with large language models for complex heterogeneous information networks [IP&M]
  Shixuan Liu, Haoxiang Cheng, Yunfei Wang, Yue He, Changjun Fan†, Zhong Liu
• Efficient Table Embeddings via Self-Supervised Structural-Semantic Graph Autoencoder [IP&M]
  Jinlong Tian, Shixuan Liu*, Ruochun Jin, Mengmeng Li, Yanfang Zhou, Xinhai Xu†, Yuhua Tang†

• Tabular Synthesis Based on Bi-Directional Feedback Conditional Diffusion Models [ICASSP 2026]
  Qiyuan Zhang, Yuhua Tang, Jinlong Tian, Yue He, Liyang Xu, Shixuan Liu†

• The Expressive Power of Graph Neural Networks: A Survey [IEEE TKDE]
  Bingxu Zhang, Changjun Fan, Shixuan Liu, Kuihua Huang, Xiang Zhao, Jincai Huang, Zhong Liu
• Toward bridging the gap between machine intelligence and machine wisdom: Dilemmas and conjectures [The Innovation]
  Rui Wang, Shixuan Liu, Changjun Fan, Guozheng Li, Jincai Huang, Zhong Liu, Gang Zhou
• A unified modeling framework for automated penetration testing [Computer & Security]
  Yunfei Wang, Shixuan Liu, Wenhao Wang, Changling Zhou, Chao Zhang, Jiandong Jin, Cheng Zhu
• RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains [NeurIPS 2025]
  Tianle Pu, Zijie Geng, Haoyang Liu, Shixuan Liu, Jie Wang, Li Zeng, Chao Chen, Changjun Fan
• Unstitching the Chimera: Frame-Level Risk and Train-Free Mitigation for Video Hallucination [CVPR 2026]
  Songyuan Yang, Guijian Tang, Kun Hu, Haotian Wang, Shixuan Liu, Wenjing Yang, Long Lan, Huibin Tan
• CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction [AAAI 2026]
  Tianle Pu, Jianing Li, Yingying Gao, Shixuan Liu, Zijie Geng, Haoyang Liu, Chao Chen, Changjun Fan
• Detecting Unobserved Confounders: A Kernelized Regression Approach [AAAI 2026]
  Yikai Chen, Yunxin Mao, Chunyuan Zheng, Hao Zou, Shanzhi Gu, Shixuan Liu, Yang Shi, Wenjing Yang, Kun Kuang, Haotian Wang
• Solving combinatorial optimization problem over graph through qubo transformation and deep reinforcement learning [ICDM 2024]
  Tianle Pu, Chao Chen, Li Zeng, Shixuan Liu, Rui Sun, Changjun Fan
• Coherence mode: Characterizing local graph structural information for temporal knowledge graph [Information Sciences]
  Yuehang Si, Xingchen Hu, Qing Cheng, Xinwang Liu, Shixuan Liu, Jincai Huang
• DLME: A distillation mechanism from language models for knowledge graph embedding [Neurocomputing]
  Yuehang Si, Xingchen Hu, Qing Cheng, Jincai Huang, Shixuan Liu