1 code implementation • 4 Jan 2024 • Mengzhao Wang, Weizhi Xu, Xiaomeng Yi, Songlin Wu, Zhangyang Peng, Xiangyu Ke, Yunjun Gao, Xiaoliang Xu, Rentong Guo, Charles Xie
In this paper, we present Starling, an I/O-efficient disk-resident graph index framework that optimizes data layout and search strategy within the segment.
1 code implementation • 11 Dec 2023 • Mengzhao Wang, Xiangyu Ke, Xiaoliang Xu, Lu Chen, Yunjun Gao, Pinpin Huang, Runkai Zhu
We investigate the problem of multimodal search of target modality, where the task involves enhancing a query in a specific target modality by integrating information from auxiliary modalities.
1 code implementation • 4 Dec 2023 • Yuxia Geng, Jiaoyan Chen, Yuhang Zeng, Zhuo Chen, Wen Zhang, Jeff Z. Pan, Yuxiang Wang, Xiaoliang Xu
Accordingly, we propose a new KGC method named PDKGC with two prompts -- a hard task prompt which is to adapt the KGC task to the PLM pre-training task of token prediction, and a disentangled structure prompt which learns disentangled graph representation so as to enable the PLM to combine more relevant structure knowledge with the text information.
1 code implementation • 30 Nov 2023 • Qiang Yue, Xiaoliang Xu, Yuxiang Wang, Yikun Tao, Xuliyuan Luo
It suffers from the large-scale $\mathcal{X}$ because a PG with full vectors is too large to fit into the memory, e. g., a billion-scale $\mathcal{X}$ in 128 dimensions would consume nearly 600 GB memory.
no code implementations • 30 Sep 2023 • Jiongkang Ni, Xiaoliang Xu, Yuxiang Wang, Can Li, Jiajie Yao, Shihai Xiao, Xuecang Zhang
The main drawback of graph-based ANNS is that a graph index would be too large to fit into the memory especially for a large-scale $\mathcal{X}$.
no code implementations • 25 Mar 2022 • Mengzhao Wang, Lingwei Lv, Xiaoliang Xu, Yuxiang Wang, Qiang Yue, Jiongkang Ni
We easily deploy existing various PGs on this framework to process hybrid queries efficiently.
1 code implementation • 29 Jan 2021 • Mengzhao Wang, Xiaoliang Xu, Qiang Yue, Yuxiang Wang
Approximate nearest neighbor search (ANNS) constitutes an important operation in a multitude of applications, including recommendation systems, information retrieval, and pattern recognition.