Introduction:

林希珣，中国科学院信息工程研究所助理研究员。入所前在百度搜索科学团队担任高级算法工程师。2022年博士毕业于中国科学院信息工程研究所，指导老师为周川副教授和王斌教授。研究方向为图表示学习、推荐系统和大语言模型。现聚焦于研究图模型和大语言模型的算法鲁棒性与决策不确定性。目前已在IEEE TKDE、TNNLS、WWW、SIGIR、ICDM、WSDM等国际顶级期刊/会议上发表一作/通讯作者论文十余篇。

Xixun Lin, a assistant research fellow of Institute of Information Engineering, Chinese Academy of Sciences. Before that, he was a senior algorithm engineer of Search Science at Baidu. He had received the Ph.D. degree from Institute of Information Engineering, Chinese Academy of Sciences in 2022 under the supervision of Prof. Chuan Zhou and Prof. Bin Wang. His research interests broadly include graph representation learning, recommender systems and large language models. Now, He is focusing on the analysis of algorithm robustness and prediction uncertainty of graph model and large language models. He has published more than ten papers in top-tier journals and conferences as the first or corresponding authors, such as IEEE TKDE, TNNLS, WWW, SIGIR, WSDM and ICDM.

Social Service:

• 1.PC for WWW-24, AAAI 24/23/22/21, IJCNN 22/21.
• 2.Reviewer for IEEE TNNLS, ACM TKDD, scientific reports.

Awards and Honors:

• 1.AIDU Talent Program, Baidu Inc.
• 2.Beijing Outstanding Graduates, Beijing Municipal Education Commission.
• 3.Pacemaker to Merit Student, UCAS.

Representative Works:

• 1.(ICML-2024) 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.
• 2.(ICML-2024) Shuai Zhang, Chuan Zhou, Yang Aron Liu, Peng Zhang, Xixun Lin, Zhi-Ming Ma. Neural Jump-Diffusion Temporal Point Processes.
• 1.(TKDE-2023) 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.
• 2.(PR-2022) 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.
• 3.(TNNLS-2022) Xixun Lin, Zhao Li, Peng Zhang, Luchen Liu, Chuan Zhou, Bin Wang. Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification.
• 4.(SIGIR-2022) Jiangxia Cao, Xixun Lin, Xin Cong, Tingwen Liu, Jing Ya, Bin Wang. Learning Disentangled Representation of Cross-Domain Recommendation.
• 5.(ICASSP-2022) Luchen liu, Xixun Lin, Peng Zhang, Lei Zhang, Bin Wang. Learning Common Dependency Structure for Unsupervised Cross-Domain NER.
• 6.(ICDM-2021, Best ranked papers) Xixun Lin, Jiangxia Cao, Peng Zhang, Chuan Zhou, Zhao Li, Jia Wu, Bin Wang. Disentangled Deep Multivariate Hawkes Process for Learning Event Sequences.
• 7.(ECML-2021) Jiangxia Cao, Xixun Lin*, Xin Cong, Shu Guo, Hengzhu Tang, Tingwen Liu, Bin Wang. Deep Structural Point Process for Learning Temporal Interaction Networks.
• 8.(WWW-2021, Candidates of Best Research Paper Awards) Xixun Lin, Jia Wu, Chuan Zhou, Shirui Pan, Yanan Cao, Bin Wang. Task-adaptive Neural Process for User Cold-Start Recommendation.
• 9.(ICASSP-2021) Luchen liu, Xixun Lin, Peng Zhang, Bin Wang. Improving Cross-domain Slot Filling with Common Syntactic Structure.
• 10.(WSDM-2021)Xixun Lin#, Jiangxia Cao#, Shu Guo, Luchen Liu, Tingwen Liu, Bin Wang. Bipartite Graph Embedding via Mutual Information Maximization.
• 11.(ICDM-2020) Xixun Lin, Chuan Zhou, Hong Yang, Jia Wu, Haibo Wang, Yanan Cao, Bin Wang. Exploratory Adversarial Attacks on Graph Neural Networks.
• 12.(ICDM-2019)Xixun Lin, Hong Yang, Jia Wu, Chuan Zhou, Bin Wang. Guiding Cross-lingual Entity Alignment via Adversarial Knowledge Embedding.
• 13.(NCAA-2019) Xixun Lin, Yanchun Liang, Fausto Giunchiglia, Xiaoyue Feng, Renchu Guan.Relation Path Embedding in Knowledge Graphs.