谢希科
研究员
邮件：xkxie@ustc.edu.cn
所属单位：生物医学工程学院
个人主页：http://staff.ustc.edu.cn/~xkxie
主要研究方向：图机器学习系统、大模型长序列推理及检索增强生成、神经数据结构与推理机制、数据探索、及相关技术在生物医学工程领域的应用。
本硕毕业于西安交通大学，博士毕业于香港大学，曾任丹麦奥尔堡大学助理教授。现任中国科学技术大学苏州高等研究院研究员、博士生导师；担任计算机学会数据库专委会委员，教育战略学会大数据专委会委员等。主要从事数据库、数据挖掘和机器学习等方面的研究工作，重点关注图计算、流计算、和数据驱动的人工智能系统与算法研究。
已在数据与人工智能领域的国际重要学术期刊（包括TPAMI、TODS、TON、VLDBJ、TKDE、TC等）及会议（包括SIGMOD、VLDB、ICDE、NeurIPS、ICML、ICLR、KDD、SC等）发表论文100余篇，其中计算机学会推荐 A类论文50余篇。曾担任过30多个大数据领域重要国际会议(包括PVLDB、ICDE、NeurIPS、ICML、ICLR、SIGIR、KDD、WWW等)的程序委员会委员，和20多个重要国际期刊(包括Nature Comm.、ACM Computing Survey、TODS、VLDBJ、TKDE等)的审稿人。主持包括3项国家自然科学基金面上项目在内的20余项课题。
近几年代表论著：
[1] Learning Graph Foundation Models on Riemannian Graph-of-Graphs. Haokun Liu, Zezhong Ding, Xike Xie*. ICML 2026
[2] Optimizing KV Cache Eviction from an Output Perturbation Perspective. Yuan Feng, Junlin Lv, Haoyu Guo, Yukun Cao, S Kevin Zhou, Xike Xie*. ICML 2026
[3] DOLPHIN: Scalable Disk–RAM–GPU Pipelined Training for Massive Temporal GNNs. Zezhong Ding, Rui Guo, Wenbo Zhen, Junlin Lv, Jianliang Xu, Xike Xie*. SC 2026
[4] SamGoG: A Sampling-Based Graph-of-Graphs Framework for Imbalanced Graph Classification. Shangyou Wang, Zezhong Ding, Xike Xie*. KDD 2026
[5] SIGHP: Scalable Information-Guided Hypergraph Partitioner. Huhao Guan, Zezhong Ding, Ao Ke, Xike Xie*, S. Kevin Zhou. KDD 2026
[6] SWIFT: Enabling Large-Scale Temporal Graph Learning on a Single Machine. Rui Guo, Zezhong Ding, Xike Xie*, Jianliang Xu. SIGMOD 2026
[7] KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering. Zhiyang Li, Ao Ke, Yukun Cao, Xike Xie*. ACL 2026
[8] Taming the Fragility of KV Cache Eviction in LLM Inference. Yuan Feng, Haoyu Guo, Junlin Lv, Xike Xie*, S Kevin Zhou. ICLR 2026
[9] Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference. Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie*, S Kevin Zhou. NeurIPS 2025
[10] DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion. Jin Li, Zezhong Ding, Xike Xie*. NeurIPS 2025
[11] LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration. Yukun Cao, Zengyi Gao, Zhiyang Li, Xike Xie*, S. Kevin Zhou, Jianliang Xu. PVLDB 2025
[12] Capsule: an Out-of-Core Training Mechanism for Colossal GNNs. Yongan Xiang, Zezhong Ding, Rui Guo, Shangyou Wang, Xike Xie*, S. Kevin Zhou. SIGMOD 2025
[13] Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams. Yuan Feng, Yukun Cao, Hairu Wang, Xike Xie*, S. Kevin Zhou. ICML 2025
[14] GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding. Yukun Cao, Shuo Han, Zengyi Gao, Zezhong Ding, Xike Xie*, S. Kevin Zhou. ACL 2025
[15] HIGGS: Hierarchy-Guided Graph Stream Summarization. Xuan Zhao, Xike Xie*, Christian Jensen. ICDE 2025
[16] ClusPar: A Game-Theoretic Approach for Efficient and Scalable Streaming Edge Partitioning. Zezhong Ding, Deyu Kong, Zhuoxu Zhang, Xike Xie*, Jianliang Xu. TC 2025
[17] Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data. Yukun Cao, Yuan Feng, Hairu Wang, Xike Xie*, S. Kevin Zhou*. TPAMI 2024
[18] Play like a Vertex: A Stackelberg Game Approach for Streaming Graph Partitioning. Zezhong Ding, Yongan Xiang, Shangyou Wang, Xike Xie*, S. Kevin Zhou. SIGMOD 2024