Chunhui Shen

Chunhui Shen

Auto-generated profile, based on publicly available information

Chunhui Shen

Alibaba Group, Hangzhou, Zhejiang, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
5 September 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YGYunjun Gao
Yunjun Gao
ZFZiquan Fang
Ziquan Fang
JXJiachen Xu
Jiachen Xu
SGShenghao Gong
Shenghao Gong
CSChunhui Shen
Chunhui Shen
LCLu Chen
Lu Chen
With the explosive ubiquity of GPS-equipped devices, e.g., mobile phones, vehicles, and vessels, a massive amount of real-time, unbounded, and varying-sampling trajectory streams are being generated continuously. Clustering trajectory streams is useful in real-life applications, such as traffic congestion prediction, crowd flow detection, and moving behavior study. Although several sliding-window based algorithms (that adopt the classic two-phases online-offline processing framework) are proposed for trajectory stream clustering, three challenges exist to meet ever-increasing application demands for effective, efficient, and scalable online clustering: i) How to effectively model unbounded trajectory streams in the online settings for effective clustering? ii) How to achieve truly real-time online processing? iii) How to improve the scalable capability of the clustering algorithm to support large-scale moving trajectory streams? In this paper, we propose an efficient and distributed trajectory stream clustering framework that can: i) model trajectory streams dynamically and effectively in a self-adaptive manner, i.e., $k$ -Segment, which considers both spatial and temporal aspects of trajectory streams, ii) support distributed indexing, processing, and workload balance, and iii) incrementally cluster trajectory streams in an efficient manner. Experiments on a wide range of real-world trajectory datasets show that our framework outperforms state-of-the-art baselines in terms of clustering quality, efficiency, and scalability.

30 May 2026
Verified
Conference Paper
Open access
YWYan Wang
Yan Wang
JZJian Zhou
Jian Zhou
SHSai Huang
Sai Huang
CDChao Dou
Chao Dou
HTHanwen Tian
Hanwen Tian
DDDong Deng
Dong Deng
Vector databases have become a cornerstone of modern AI infrastructure, enabling semantic retrieval and retrieval-augmented generation (RAG) over massive unstructured datasets. However, existing systems face an inherent trade-off: specialized vector databases deliver low-latency in-memory search but struggle with scalability and integration with structured data, whereas general-purpose databases provide consistency and fault tolerance at the cost of query performance. In this paper, we present LindormVector, a distributed, scalable, and cost-efficient vector engine built natively on Lindorm, Alibaba Cloud's multi-model, cloud-native NoSQL database. LindormVector adopts a shared-storage architecture where all data is persisted in a distributed file system for elasticity, durability, and high availability. To minimize I/O operations, network communication, and memory footprint, LindormVector adopts an IVFPQ-style index tailored to Lindorm's storage model. A key distinction in our index design lies in the number of clusters nlist. We observe that the optimal number of clusters is often substantially larger than the conventional sqrt(n) rule-of-thumb for a dataset of n vectors, especially when n is large. To guide the choice of nlist, we develop a practical cost model capturing the trade-off between centroid search and code scan costs. To efficiently support large nlist values, LindormVector accelerates K-Means clustering via approximate nearest neighbor search, organizes centroids with an HNSW graph, and introduces an optimized greedy graph traversal for efficient centroid search. LindormVector further supports real-time index updates and efficient filtered and hybrid vector search. Extensive experiments on billion-scale datasets demonstrate that LindormVector consistently achieves high recall with millisecond-level latency and significantly outperforms both specialized and general-purpose vector databases including Milvus, Elasticsearch, and PGVector. LindormVector is already deployed in production across Alibaba Cloud, where the largest cluster consists of hundreds of ECS instances and manages more than 100 billion vectors.

8 August 2026
Verified
Conference Paper
Open access
LKLingdu Kong
Lingdu Kong
XYXiaochun Yang
Xiaochun Yang
SLShuo Li
Shuo Li
TLTieying Li
Tieying Li
NUNORTHEASTERN UNIVERSITY
NORTHEASTERN UNIVERSITY
FLFeibo Li
Feibo Li

18 May 2026 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
SLShuo Li
Shuo Li
XYXiaochun Yang
Xiaochun Yang
CSChunhui Shen
Chunhui Shen
YHYutong Han
Yutong Han
XWXiang Wang
Xiang Wang
FLFeibo Li
Feibo Li
To address the dual challenges of data transmission and storage in Internet of Things (IoT) systems, the development of efficient streaming lossless compression algorithms for floating-point data has become a critical research focus. Existing XOR-based floating-point compression algorithms adopt a fixed reference selection strategy by using the immediate predecessor value as the reference. Usually, this choice is not the best, as earlier values in the data stream often provide more similar and effective references. Based on this observation, we propose dynamically searching previous values to identify the reference value that yields the best compression results for the current value. To this end, we present Kangaroo, an efficient lossless compression algorithm for floating-point time series that implements a dynamic reference selection. Our approach begins by establishing optimal reference selection criteria aimed at minimizing the number of encoded bits, introducing a pruning-based encoding strategy to reduce encoding overhead. We further propose a dynamic search strategy that selects reference values from an extended historical window, skipping historical data that generates suboptimal XOR results. This strategy enables precise identification of the suitable reference value while improving search efficiency. Additionally, we design a bit-flip-based erasure strategy to maximize trailing zeros, thereby comprehensively enhancing compression performance. Extensive experiments on 26 datasets demonstrate that Kangaroo outperforms all baseline methods across all evaluation metrics. Most notably, compared to state-of-the-art streaming compression algorithms, our algorithm achieves a 23.2% average improvement (peaking at 98.0% ) in compression ratio, with compression and decompression speeds averaging 2.13× and 2.21× (reaching up to 11.75× and 5.24×) of the baseline, respectively. This novel solution establishes comprehensive performance leadership in floating-point time-series compression, and has been applied to the Lindorm database on Alibaba Cloud since 2024, managing tens of petabytes of Internet of Vehicles (IoV) data.