Xiaoliang Xu

Prof. Dr. Xiaoliang Xu

orcid

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2020 in Neural Computation
Verified
Journal Article
Closed access
XJXiping Ju
Xiping Ju
BFBiao Fang
Biao Fang
RYRui Yan
Rui Yan
XXXiaoliang Xu
Xiaoliang Xu
HTHuajin Tang
Huajin Tang
A spiking neural network (SNN) is a type of biological plausibility model that performs information processing based on spikes. Training a deep SNN effectively is challenging due to the nondifferention of spike signals. Recent advances have shown that high-performance SNNs can be obtained by converting convolutional neural networks (CNNs). However, the large-scale SNNs are poorly served by conventional architectures due to the dynamic nature of spiking neurons. In this letter, we propose a hardware architecture to enable efficient implementation of SNNs. All layers in the network are mapped on one chip so that the computation of different time steps can be done in parallel to reduce latency. We propose new spiking max-pooling method to reduce computation complexity. In addition, we apply approaches based on shift register and coarsely grained parallels to accelerate convolution operation. We also investigate the effect of different encoding methods on SNN accuracy. Finally, we validate the hardware architecture on the Xilinx Zynq ZCU102. The experimental results on the MNIST data set show that it can achieve an accuracy of 98.94% with eight-bit quantized weights. Furthermore, it achieves 164 frames per second (FPS) under 150 MHz clock frequency and obtains 41[ ] speed-up compared to CPU implementation and 22 times lower power than GPU implementation.

12 March 2024 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
MWMengzhao Wang
Mengzhao Wang
WXWeizhi Xu
Weizhi Xu
XYXiaomeng Yi
Xiaomeng Yi
SWSonglin Wu
Songlin Wu
ZPZhangyang Peng
Zhangyang Peng
CXCharles Xie
Charles Xie
High-dimensional vector similarity search (HVSS) is gaining prominence as a powerful tool for various data science and AI applications. As vector data scales up, in-memory indexes pose a significant challenge due to the substantial increase in main memory requirements. A potential solution involves leveraging disk-based implementation, which stores and searches vector data on high-performance devices like NVMe SSDs. However, implementing HVSS for data segments proves to be intricate in vector databases where a single machine comprises multiple segments for system scalability. In this context, each segment operates with limited memory and disk space, necessitating a delicate balance between accuracy, efficiency, and space cost. Existing disk-based methods fall short as they do not holistically address all these requirements simultaneously. 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. It has two primary components: (1) a data layout incorporating an in-memory navigation graph and a reordered disk-based graph with enhanced locality, reducing the search path length and minimizing disk bandwidth wastage; and (2) a block search strategy designed to minimize costly disk I/O operations during vector query execution. Through extensive experiments, we validate the effectiveness, efficiency, and scalability of Starling. On a data segment with 2GB memory and 10GB disk capacity, Starling can accommodate up to 33 million vectors in 128 dimensions, offering HVSS with over 0.9 average precision and top-10 recall rate, and latency under 1 millisecond. The results showcase Starling's superior performance, exhibiting 43.9x higher throughput with 98% lower query latency compared to state-of-the-art methods while maintaining the same level of accuracy.

24 December 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
YGYuxia Geng
Yuxia Geng
JCJiaoyan Chen
Jiaoyan Chen
YZYuhang Zeng
Yuhang Zeng
ZCZhuo Chen
Zhuo Chen
WZWen Zhang
Wen Zhang
XXXiaoliang Xu
Xiaoliang Xu

11 August 2010 in IET Radar, Sonar & Navigation
Verified
Journal Article
Closed access
YZY. Zhang
Y. Zhang
ZYZ. Ye
Z. Ye
XXXiaoliang Xu
Xiaoliang Xu
JCJ. Cui
J. Cui
In this study, a low complexity two-dimensional direction-of-arrival (2-D DOA) estimation method is proposed with uniform rectangular array (URA) when uncorrelated and coherent signals coexist. By using a new method of modified estimation of signal parameters via rotation invariance techniques (ESPRIT), the DOAs of uncorrelated signals are first estimated. Afterwards, the contributions of uncorrelated signals are eliminated, and then a new Toeplitz matrix without the information of uncorrelated signals is constructed. Using the product of the Toeplitz matrix and its conjugate transpose matrix, the remaining coherent signals can be resolved. With the two-step processing, the proposed method can resolve more signals with low computational complexity. Simulation results demonstrate the effectiveness and efficiency of the proposed method. The Cramer–Rao bound (CRB) for this signal scenario is also derived.

10 July 2024
Verified
Conference Paper
Open access
YWYuxiang Wang
Yuxiang Wang
XGXiaoxuan Gou
Xiaoxuan Gou
XXXiaoliang Xu
Xiaoliang Xu
YGYuxia Geng
Yuxia Geng
XKXiangyu Ke
Xiangyu Ke
XWXiangying Wu
Xiangying Wu
Given a graph G and a query node q, community search (CS) aims to find a structurally cohesive subgraph from G that contains q. CS is widely used in many real-world applications, such as online recommendation and expert finding. Recently, the rise of learning-based CS methods has garnered extensive research interests, showcasing the promising potential of neural solutions. However, there remains room for optimization: (1) They initialize node features via classical methods, e.g., one-hot, random, and position encoding, which may fall short in capturing valuable community cohesiveness-related features. (2) The reliance on GCN or GCN-like models poses challenges in scaling to large graphs. (3) Existing methods do not adapt well to dynamic graphs, often requiring retraining from scratch. To handle this, we present CSFormer, a scalable CS based on Graph Transformer. First, we present a novel l-hop neighborhood community vector based on n-order h-index to represent each node's community features, generating a sequence of feature vectors by varying the neighborhood scope l. Then, we build a Transformer backbone to learn a good graph embedding that carries rich community features, based on which we perform a prediction-filtering-based online CS to efficiently return a community of q. We extend CSFormer to dynamic graphs and various community models. Extensive experiments on seven real-world graphs show our solution's superiority on effectiveness, e.g., we attain an average improvement of 20.6% in F1-score compared to the latest competitors.

22 March 2023 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
YWYuxiang Wang
Yuxiang Wang
JLJun Liu
Jun Liu
XXXiaoliang Xu
Xiaoliang Xu
XKXiangyu Ke
Xiangyu Ke
Tianxing WuTianxing Wu
Tianxing Wu
XGXiaoxuan Gou
Xiaoxuan Gou
Expert finding is crucial for a wealth of applications in both academia and industry. Given a user query and trove of academic papers, expert finding aims at retrieving the most relevant experts for the query, from the academic papers. Existing studies focus on embedding-based solutions that consider academic papers’ textual semantic similarities to a query via document representation and extract the top- n experts from the most similar papers. Beyond implicit textual semantics, however, papers’ explicit relationships (e.g., co-authorship) in a heterogeneous graph (e.g., DBLP) are critical for expert finding, because they help improve the representation quality. Despite their importance, the explicit relationships of papers generally have been ignored in the literature. In this article, we study expert finding on heterogeneous graphs by considering both the explicit relationships and implicit textual semantics of papers in one model. Specifically, we define the cohesive ( k , 𝒫)-core community of papers w.r.t. a meta-path 𝒫 (i.e., relationship) and propose a ( k , 𝒫)-core based document embedding model to enhance the representation quality. Based on this, we design a proximity graph-based index (PG-Index) of papers and present a threshold algorithm (TA)-based method to efficiently extract top- n experts from papers returned by PG-Index. We further optimize our approach in two ways: (1) we boost effectiveness by considering the ( k , 𝒫)-core community of experts and the diversity of experts’ research interests, to achieve high-quality expert representation from paper representation; and (2) we streamline expert finding, going from “extract top- n experts from top- m ( m> n ) semantically similar papers” to “directly return top- n experts”. The process of returning a large number of top- m papers as intermediate data is avoided, thereby improving the efficiency. Extensive experiments using real-world datasets demonstrate our approach’s superiority.