New Zilliz Research on Vector Data Management Accepted by SIGMOD
By Zilliz on Mar 09, 2021
It is with great pleasure that we announce our recent research paper, Milvus: A Purpose-built Vector Data Management System, has been accepted by the 2021 ACM SIGMOD/PODS Conference. The paper was recognized for its advanced work in vector data management, and its authors will be giving a keynote presentation at the SIGMOD Conference taking place from June 20-25 in Xi’an, China. Milvus was launched by Zilliz in 2019 and is currently an incubation-stage project at the LF AI & Data Foundation.
SIGMOD is the Association for Computing Machinery’s Special Interest Group on Management of Data, which specializes in large-scale data management problems. The annual ACM SIGMOD Conference, which began in 1975, is a leading international forum for database researchers, practitioners, developers, and users to explore cutting-edge ideas and to exchange techniques, tools, and experiences. With an average acceptance rate of 17.4%, the annual ACM SIGMOD/PODS Conference is highly selective.
Milvus : A Purpose-built Vector Data Management System has been recognized by SIGMOD’s review committee for introducing an end-to-end solution for vector similarity search. Milvus offers a modern design and implementation, such as query processing over structured attributes and multiple vectors, as well as improved heterogeneous computing efficiency.
“This research offers a significant system design level breakthrough for vector data management,” said SIGMOD’s review committee. “Milvus supports real-time search on dynamic data and diversified search requirements that apply to a variety of business scenarios. As an open-source project, Milvus outperforms most competing vector databases. The committee found this research paper both inspiring and enlightening.”
“As the world’s first open-source vector database system, Milvus has developed rapidly over the past two years to become one of the most active, influential, and widely used projects under LF AI & Data Foundation,” said Charles Xie, Chairperson of LF AI & Data Governing Board, and Founder of Zilliz. “Milvus’ recognition by SIGMOD validates its technology and software architecture among academia, as well as the database industry at large. As an open-source project, Milvus has been successfully deployed in applications spanning new drug discovery, biometric analysis, and much more. I look forward to the ongoing and ever-evolving progress made by the Milvus project and its community, to propel AI unstructured data processing to new heights.”
The paper is now available for download.
Zilliz is the company behind Milvus, the world’s most popular vector similarity search engine, to accelerate the development of next-generation data fabric. Milvus is currently an incubation-stage project at the LF AI & Data Foundation and has been deployed by over 600 global users. The platform’s efficiency and reliability simplify the process of deploying AI and MLOps at scale.
Zilliz is on a mission to make sense of unstructured data through open-source and cloud-native solutions. Our technology has broad applications spanning new drug discovery, computer vision, recommendation engines, chatbots, and much more.
Official Zilliz family logos and assets for download.
For media and analyst inquiries.