以下文章来源于港科大广州 I 数据科学与分析 ，作者DSA

港科广数据科学与分析学域及港科大计算机科学与工程学系19篇论文入选数据库顶会ACM SIGMOD 2023
2023年6月18-23日，数据库领域顶级会议ACM SIGMOD 2023于美国西雅图顺利举行。于本次会议上，香港科技大学（广州）数据科学与分析学域与香港科技大学计算机科学与工程学系师生共有19篇论文成功入选。
ACM SIGMOD 会议作为数据库系统领域历史最悠久且最权威的学术会议，是从事该领域的学者、研究人员、从业者等探索前沿思想和成果并交流技术、工具和经验的领先国际论坛。本年度ACM SIGMOD共有660篇投稿，录用186篇。

以下为入选论文简介：

异构特征空间上的增量表格学习Incremental Tabular Learning on Heterogeneous Feature Space

Hanmo Liu (The Hong Kong University of Science and Technology (Guangzhou))*; Shimin Di (The Hong Kong University of Science and Technology); Lei Chen (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou))

https://dl.acm.org/doi/10.1145/3588698

用于解决降雨空间插值问题的自监督学习方法SSIN: Self-Supervised Learning for Rainfall Spatial Interpolation

Jia Li (The Hong Kong University of Science and Technology)*; Yanyan Shen (Shanghai Jiao Tong University); Lei Chen (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou)); Charles Wang Wai Ng (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou))

https://dl.acm.org/doi/10.1145/3589321

成对有效电阻的有效估计Efficient Estimation of Pairwise Effective Resistance

Renchi Yang (The Hong Kong Baptist University)*; Jing Tang (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou))

https://dl.acm.org/doi/10.1145/3588696

LiteHST：基于树嵌入的相似性搜索方法LiteHST: A Tree Embedding based Method for Similarity Search

Yuxiang Zeng (The Hong Kong University of Science and Technology)*; Yongxin Tong (Beihang University); Lei Chen (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou))

https://dl.acm.org/doi/10.1145/3588715

TED：图数据库中发现top-k多样化边模式的方法TED: Towards Discovering Top-𝑘 Edge-Diversified Patterns in a Graph Database

Kai Huang (The Hong Kong University of Science and Technology)*; Haibo Hu (Hong Kong Polytechnic University); Qingqing Ye (Hong Kong Polytechnic University); Kai Tian (Tencent); Bolong Zheng (Huazhong University of Science and Technology); Xiaofang Zhou (The Hong Kong University of Science and Technology)

https://dl.acm.org/doi/10.1145/3588736

Orca：具有理论保证的可扩展时态图神经网络训练方法

Orca: Scalable Temporal Graph Neural Network Training with Theoretical Guarantees

Yiming Li (The Hong Kong University of Science and Technology)*; Yanyan Shen (Shanghai Jiao Tong University); Lei Chen (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou)); Mingxuan Yuan (Huawei)

https://dl.acm.org/doi/abs/10.1145/3588737

EARLY：用于动态图的高效可靠的图神经网络EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs

Haoyang Li (The Hong Kong University of Science and Technology); Lei Chen (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou))

https://dl.acm.org/doi/10.1145/3589308

DUCATI: 一个针对巨型图上的图神经网络设计的基于GPU的双缓存训练系统DUCATI: A Dual-Cache Training System for Graph Neural Networks on Giant Graphs with GPU

Xin Zhang (The Hong Kong University of Science and Technology); Yanyan Shen (Shanghai Jiao Tong University); Yingxia Shao (BUPT); Lei Chen (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou));

https://dl.acm.org/doi/10.1145/3589311

由 GPU 加速的快速子图匹配方法Efficient GPU-Accelerated Subgraph Matching

Xibo Sun (Hong Kong University of Science and Technology); Qiong Luo (The Hong Kong University of Science and Technology & The Hong Kong University of Science and Technology  (Guangzhou))

https://dl.acm.org/doi/10.1145/3589326

HAIPipe：融合人工生成和机器生成的数据管道HAIPipe: Combining Human-generated and Machine-generated Pipelines for Data Preparation

Sibei Chen (Renmin University of China); Nan Tang (QCRI / The Hong Kong University of Science and Technology  (Guangzhou)); Ju Fan (Renmin University of China); Xuemi Yan (Renmin University of China); Chengliang Chai (Beijing Institute of Technology); Guoliang Li (Tsinghua University); Xiaoyong Du (Renmin University of China)

https://dl.acm.org/doi/10.1145/3588945

GoodCore：基于不完整数据的核心子集选择以实现数据高质高效的机器学习GoodCore: Coreset Selection over Incomplete Data for Data-effective and Data-efficient Machine Learning

Chengliang Chai (Beijing Institute of Technology); Jiabin Liu (Beijing Institute of Technology); Nan Tang (QCRI / The Hong Kong University of Science and Technology (Guangzhou)); Ju Fan (Renmin University of China); Dongjing Miao (Harbin Institute of Technology); Jiayi Wang (Tsinghua University); Yuyu Luo (Tsinghua University); Guoliang Li (Tsinghua University)

https://dl.acm.org/doi/10.1145/3589302

Unicorn: 支持数据集成匹配任务的统一多任务模型Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration

Jianhong Tu (Renmin University of China); Ju Fan (Renmin University of China); Nan Tang (QCRI / The Hong Kong University of Science and Technology (Guangzhou)); Peng Wang (Renmin University of China); Guoliang Li (Tsinghua University); Xiaoyong Du (Renmin University of China); Xiaofeng Jia (Beijing Big Data Center); Song Gao (Beijing Big Data Center)

https://dl.acm.org/doi/abs/10.1145/3588938

使用结构和内容提示学习的小数据文本到 SQL 翻译Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning

Zihui Gu (Renmin University of China); Ju Fan (Renmin University of China); Nan Tang (QCRI / The Hong Kong University of Science and Technology (Guangzhou)); Lei Cao (MIT / University of Arizona); Bowen Jia (Renmin University of China); Sam Madden (MIT), Xiaoyong Du (Renmin University of China)

https://dl.acm.org/doi/10.1145/3589292

面向相似性搜索的数据感知的学习型折线图表示Learned Data-aware Image Representations of Line Charts for Similarity Search

Yuyu Luo (Tsinghua University / The Hong Kong University of Science and Technology (Guangzhou)); Yihui Zhou (Tsinghua University); Nan Tang (QCRI / The Hong Kong University of Science and Technology (Guangzhou)); Guoliang Li (Tsinghua University); Chengliang Chai (Beijing Institute of Technology); Leixian Shen (Tsinghua University)

https://dl.acm.org/doi/10.1145/3588942

EAR-Oracle：在地形表面上任意点之间查询距离的高效索引方法EAR-Oracle: On Efficient Indexing for Distance Queries between Arbitrary Points on Terrain Surface

Bo Huang (Southern University of Science and Technology); Victor Junqiu Wei (Hong Kong Polytechnic University)*; Raymond Chi-Wing Wong (The Hong Kong University of Science and Technology); Bo Tang (Southern University of Science and Technology)

https://dl.acm.org/doi/abs/10.1145/3588694

优于组合：如何在考虑差分隐私的同时回应多个关系查询Better than Composition: How to Answer Multiple Relational Queries under Differential Privacy

Wei Dong (The Hong Kong University of Science and Technology); Dajun Sun (The Hong Kong University of Science and Technology); Ke Yi (The Hong Kong University of Science and Technology);

https://dl.acm.org/doi/10.1145/3589268

可扩展且快速在大型图上进行全图 GNN 训练的方法

Scalable and Efficient Full-Graph GNN Training for Large Graphs

Xinchen Wan (The Hong Kong University of Science and Technology); Kaiqiang Xu (The Hong Kong University of Science and Technology); Xudong Liao (The Hong Kong University of Science and Technology); Yilun Jin (The Hong Kong University of Science and Technology); Kai Chen (The Hong Kong University of Science and Technology); Xin Jin (Peking University);

https://dl.acm.org/doi/10.1145/3589288

QHL：一种用于道路网络上的精确搜索受约束的最短路径的快速算法QHL: A Fast Algorithm for Exact Constrained Shortest Path Search on Road Networks

Libin Wang (The Hong Kong University of Science and Technology); Raymond Chi-Wing Wong (The Hong Kong University of Science and Technology);

https://dl.acm.org/doi/10.1145/3589300

XInsight：从因果关系的角度进行可解释的数据分析XInsight: eXplainable Data Analysis Through The Lens of Causality

Pingchuan Ma (The Hong Kong University of Science and Technology); Rui Ding (Microsoft Research); Shuai Wang (The Hong Kong University of Science and Technology); Shi Han (Microsoft Research); Dongmei Zhang (Microsoft Research Asia);

https://dl.acm.org/doi/10.1145/3589301

来源：港科大广州 I 数据科学与分析