Introduction:

Xixun Lin is currently an Assistant Professor at the Institute of Information Engineering, Chinese Academy of Sciences (IIE, CAS), where he works closely with Prof. Yanan Cao. Prior to his current appointment, he was a senior algorithm engineer at Baidu Inc. He received his Ph.D. degree from IIE in 2022 under the supervision of Prof. Chuan Zhou and Prof. Bin Wang. His research focuses on trustworthy machine learning, with a particular emphasis on trustworthy graph neural networks, trustworthy LLM-based agents, and LLM safety. He has published several papers in top-tier journals and conferences, including IEEE TKDE, IEEE TNNLS, ACM TOIS, ICML, WWW, KDD, AAAI, and SIGIR. His work was selected as a Best Paper Candidate at both ICDM 2021 and WWW 2021.

He welcomes collaborators interested in pursuing meaningful research. Please feel free to contact him if you are interested. For a more detailed profile, please visit his personal homepage.

Academic Services:

• Program Committee Member: TPAMI, TKDE, TNNLS, TKDD, NN, ICML, ICLR, NeurIPS, KDD, WWW, CVPR, ACL, AAAI, ICDM, CIKM, etc.

Research Funding:

• Subsystem of National Major Engineering Project Phase II, CNCERT/CC — Principal Investigator.
• Research on Graph Foundation Model for Graph Anomaly Detection, China Postdoctoral Science Foundation — Principal Investigator.
• Study on Graph Meta-learning for Few-shot Graph Classification, National Natural Science Funds of China — Principal Investigator.
• Subsystem of National Major Engineering Project Phase I, CNCERT/CC — Principal Investigator.
• Research on Automatic Machine Learning Models for Graph Anomaly Detection, National Natural Science Funds of China — Key Team Member.
• Coordinate System and Multi-scale Subdivision Method for Cyberspace, Subproject of National Key R&D Program — Key Team Member.

Awards and Honors:

• 2025. 4th Place Nationwide in the Smart Social Governance Track of the 5th Social Computing Innovation Competition.
• 2025. Outstanding KDD Reviewer.
• 2023. Quarterly Outstanding Team Award, Baidu Inc.
• 2022. AIDU Talent Program, Baidu Inc.
• 2022. Beijing Outstanding Graduates, Beijing Municipal Education Commission.
• 2021. Pacemaker to Merit Student, UCAS.
• 2021. Best Ranked Papers in ICDM.
• 2021. Candidates of Best Research Paper Awards in WWW.

Representative Works:

• (TOIS2026) Hong Zhou, Xixun Lin, Yanan Cao, Shichao Zhu, Renqi Jia, Xiangyu Zhao, Guandong Xu, Li Guo. D2TCDR: Disentangled Diffusion-Based Transfer for Cross-Domain Recommendation
• (ACL2026) Yilong Liu, Xixun Lin, Pengfei Cao, Ge Zhang, Fang Fang, Yanan Cao. Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
• (ACL2026) Yixuan Nan, Xixun Lin, Yanmin Shang, Ge Zhang, Zheng Fang, Fang Fang, Yanan Cao. EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment
• (ACL2026) Yongxuan Wu, Xixun Lin, He Zhang, Nan Sun, Kun Wang, Chuan Zhou, Shirui Pan, Yanan Cao. CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
• (AAAI2026) Yu Liu, Xixun Lin, Yanmin Shang, Yangxi Li, Shi Wang, Yanan Cao. PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models.
• (EMNLP2025) Yu Liu, Yanan Cao, Xixun Lin, Yanmin Shang, Shi Wang, Shirui Pan. Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning.
• (ECAI2025) Yixuan Nan, Xixun Lin, Yanmin Shang, Zhuofan Li, Can Zhao, Yanan Cao. RANA: Robust Active Learning for Noisy Network Alignment.
• (ECML2025) Nan Sun, Xixun Lin*, Zhiheng Zhou, Yanmin Shang, Zhenlin Cheng, Yanan Cao. Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphs.
• (ACL2025) Xiaowei Zhu, Yubing Ren, Yanan Cao, Xixun Lin, Fang Fang, Yangxi Li. Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction.
• (KDD2025) Yongxuan Wu, Yang Liu, Xixun Lin, Hong Zhou, Yanan Cao, Lixin Zou, Yanmin Shang, Yanbing Liu. FairCDR: Transferring Fairness and User Preferences for Cross-Domain Recommendation.
• (TOIS2025) Xixun Lin, Rui Liu, Yanan Cao, Lixin Zou, Qian Li, Yongxuan Wu, Yang Liu, Dawei Yin, Guandong Xu. Contrastive Modality-Disentangled Learning for Multimodal Recommendation.
• (WWW2025) Xixun Lin, Yanan Cao, Nan Sun, Lixin Zou, Chuan Zhou, Peng Zhang, Shuai Zhang, Ge Zhang, Jia Wu. Conformal Graph-level Out-of-distribution Detection with Adaptive Data Augmentation.
• (AAAI2025) Chuancheng Song, Xixun Lin, Hanyang Shen, Yanmin Shang, Yanan Cao. UniFORM: Towards Unified Framework for Anomaly Detection on Graphs.
• (WWWJ2024) Yanan Cao, Xixun Lin*, Yongxuan Wu, Fengzhao Shi, Yanmin Shang, Qingfeng Tan, Chuan Zhou, Peng Zhang. A Data-centric Framework of Improving Graph Neural Networks for Knowledge Graph Embedding.
• (ICDM2024) Yang Liu, Chuan Zhou, Peng Zhang, Zhao Li, Shuai Zhang, Xixun Lin, Xindong Wu. CL4CO: A Curriculum Training Framework for Graph-based Neural Combinatorial Optimization.
• (ICML2024) Xixun Lin, Wenxiao Zhang, Fengzhao Shi, Chuan Zhou, Lixin Zou, Xiangyu Zhao, Dawei Yin, Shirui Pan, Yanan Cao. Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification.
• (ICML2024) Shuai Zhang, Chuan Zhou, Yang Aron Liu, Peng Zhang, Xixun Lin, Zhi-Ming Ma. Neural Jump-Diffusion Temporal Point Processes.
• (TKDE2023) Xixun Lin, Chuan Zhou, Jia Wu, Lixin Zou, Shirui Pan, Yanan Cao, Bin Wang, Shuaiqiang Wang, Dawei Yin. Towards Flexible and Adaptive Neural Process for Cold-start Recommendation.
• (PR2022) Xixun Lin, Chuan Zhou, Jia Wu, Hong Yang, Haibo Wang, Yanan Cao, Bin Wang. Exploratory Adversarial Attacks on Graph Neural Networks for Semi-Supervised Node Classification.
• (TNNLS2022) Xixun Lin, Zhao Li, Peng Zhang, Luchen Liu, Chuan Zhou, Bin Wang. Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification.
• (SIGIR2022) Jiangxia Cao, Xixun Lin, Xin Cong, Tingwen Liu, Jing Ya, Bin Wang. Learning Disentangled Representation of Cross-Domain Recommendation.
• (ICASSP2022) Luchen liu, Xixun Lin, Peng Zhang, Lei Zhang, Bin Wang. Learning Common Dependency Structure for Unsupervised Cross-Domain NER.
• (ICDM2021) Xixun Lin, Jiangxia Cao, Peng Zhang, Chuan Zhou, Zhao Li, Jia Wu, Bin Wang. Disentangled Deep Multivariate Hawkes Process for Learning Event Sequences. (Best ranked papers)
• (ECML2021) Jiangxia Cao, Xixun Lin*, Xin Cong, Shu Guo, Hengzhu Tang, Tingwen Liu, Bin Wang. Deep Structural Point Process for Learning Temporal Interaction Networks.
• (WWW2021) Xixun Lin, Jia Wu, Chuan Zhou, Shirui Pan, Yanan Cao, Bin Wang. Task-adaptive Neural Process for User Cold-Start Recommendation. Candidates of Best Research Paper Awards
• (ICASSP2021) Luchen liu, Xixun Lin, Peng Zhang, Bin Wang. Improving Cross-domain Slot Filling with Common Syntactic Structure.
• (WSDM2021)Xixun Lin#, Jiangxia Cao#, Shu Guo, Luchen Liu, Tingwen Liu, Bin Wang. Bipartite Graph Embedding via Mutual Information Maximization.
• (ICDM2020) Xixun Lin, Chuan Zhou, Hong Yang, Jia Wu, Haibo Wang, Yanan Cao, Bin Wang. Exploratory Adversarial Attacks on Graph Neural Networks.
• (ICDM2019)Xixun Lin, Hong Yang, Jia Wu, Chuan Zhou, Bin Wang. Guiding Cross-lingual Entity Alignment via Adversarial Knowledge Embedding.
• (NCAA2019) Xixun Lin, Yanchun Liang, Fausto Giunchiglia, Xiaoyue Feng, Renchu Guan.Relation Path Embedding in Knowledge Graphs.