Yi-Fan Zhu

MSG: a unified multi-space graph index for efficient high-dimensional multi-vector search

OneDB: A Distributed Multi-Metric Data Similarity Search System

OneDB is presented, a distributed framework for multi-metric similarity search that integrates data management with learning-based techniques and captures user intent effectively, achieving 12.63%--30.75% higher accuracy and 2.75× faster retrieval speeds compared to state-of-the-art vector search systems.

ECHO: Adaptive Community Search over Multimodal Graphs

An adaptive community search framework ECHO is proposed, which consistently outperforms state-of-the-art methods in terms of community quality while achieving superior search efficiency.

ECHO: Adaptive Community Search over Multimodal Graphs

In this paper, for the first time, we study the community search problem over multimodal graphs. This task aims to identify a query vertex-containing subgraph that is both structurally cohesive and semantically coherent with multimodal query inputs (e.g., text and images). Existing community search methods fail to capt...