Yinan Li

Yinan Li

Auto-generated profile, based on publicly available information

Yinan Li

Big Data Institute, Central South University, Changsha 410075, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
19 April 2022 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
HZHuilai Zhi
Huilai Zhi
Jinhai LiJinhai Li
Jinhai Li
YLYinan Li
Yinan Li
Uncertainties are widespread in real-world situations. In the existing studies, the uncertainties expressed by the agents engaged in a conflict situation have been extensively investigated. However, from an outsiders perspective, to what extent these agents can be trusted which is often ignored and seldom taken into account. To manage these two sides of uncertainties, we propose a mathematical framework for multi-level conflict analysis from an outsiders perspective. Concretely, in order to indicate the analysis levels and manage the conflict situation in an extent-intent view, we resort to fuzzy concept analysis. At first, we explain what is multi-level data analysis. After that, based on fuzzy concept lattices, we present a general framework for multi-level conflict analysis and a method for computing the maximal coalitions and minimum conflict sets which matter a lot in multi-level conflict analysis. And then, we describe how to update conflict analysis result when increasing the analysis levels. Experimental analysis shows that managing two sides of uncertainties can bring much more conflict resolution, and increasing analysis levels is helpful for postponing a decision making and bringing more economical conflict resolutions. Finally, case studies are made to show the application of multilevel conflict analysis model and some interesting findings are obtained. Specifically, once the cost of increasing analysis levels is taken into consideration, it is interesting to choose the optimal analysis level for making the most economic decision. That is to say, when the current decision stage is less than the optimal analysis level, it is better to delay making a decision; when the current decision stage is equal to or greater than the optimal analysis level, it is better to make a decision immediately. The main contribution of this study is the model of multi-level conflict analysis based on fuzzy concept lattices, which can incorporate the uncertainties of two sides. Our work will provide cognitive research method to the fuzzy information systems by using the merits of fuzzy concept analysis.

9 June 2021
Verified
Conference Paper
Open access
JDJialin Ding
Jialin Ding
UMUmar Farooq Minhas
Umar Farooq Minhas
BCBadrish Chandramouli
Badrish Chandramouli
CWChi Wang
Chi Wang
YLYinan Li
Yinan Li
TKTim Kraska
Tim Kraska
Today, businesses rely on efficiently running analytics on large amounts of operational and historical data to gain business insights and competitive advantage. Increasingly, such analytics are run using cloud-based data analytics services, such as Google BigQuery, Microsoft Azure Synapse, Amazon Redshift, and Snowflake. These services persist and process data in compressed, columnar formats, stored in large blocks, each of which contains thousands or millions of records. For these services, disk I/O from (remote) cloud storage is often one of the dominant costs for query processing. To reduce the amount of I/O, services often maintain per-block metadata, such as zone maps, which are used to skip blocks that are irrelevant to the query, leading to lower query execution times. However, the effectiveness of block skipping via zone maps is dependent on how the records are assigned to blocks. Recent work on instance-optimized data layouts aims to maximize block skipping by specializing the block assignment strategy to a specific dataset and workload. However, these existing approaches only optimize the layout for a single table. In this paper, we propose MTO, an instance-optimized data layout framework that determines the blocking strategy for all tables in a multi-table database in the presence of joins, such as in a star or snowflake schema common in real-world workloads. MTO takes advantage of sideways information passing through joins to jointly optimize the layout for all tables, which results in better block skipping and hence reduced query execution times. Experiments on a commercial cloud-based analytics service show that MTO achieves up to 93% reduction in blocks accessed and 75% reduction in end-to-end query times compared to alternative blocking strategies.

9 January 2025 in Information Processing & Management
Verified
Journal Article
Closed access
YLYinan Li
Yinan Li
JLJun Long
Jun Long
YHYouyuan Huang
Youyuan Huang
ZYZhan Yang
Zhan Yang

18 January 2024 in Information Sciences
Verified
Journal Article
Closed access
HZHuilai Zhi
Huilai Zhi
ZQZhenhao Qi
Zhenhao Qi
YLYinan Li
Yinan Li

11 June 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YLYinan Li
Yinan Li
JLJun Long
Jun Long
ZTZerong Tu
Zerong Tu
ZYZhan Yang
Zhan Yang

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YLYinan Li
Yinan Li
JLJun Long
Jun Long
ZYZhan Yang
Zhan Yang
Hashing has been widely applied in large-scale multimodal retrieval by mapping heterogeneous modalities data into binary codes. However, most cross-modal hashing methods cannot make the most of semantic information to construct the association relations of sample pairs, resulting in unsatisfactory retrieval accuracy. Concept lattice is a powerful tool for data mining and information retrieval, and for all we know, this is the first time to combine formal concept analysis and hash learning to improve cross-modal hashing retrieval performance. In this paper, we propose a novel framework for Asymmetric Cross-modal Hashing based on Formal Concept Analysis, denoted as ACHFCA. Initially, a flash-projection three-layer semantic enhancement descriptor is designed to extract latent representations from heterogeneous modalities. Subsequently, an asymmetric hash learning framework is established to enhance the semantics of different layers based on the fine-grained similarity values reconstructed from concept lattice to reinforce the discriminative competence of the model. Finally, an effective discrete optimization algorithm is proposed, which can directly learn compact hash codes. Comprehensive experiments on MIRFlickr, NUS-WIDE and IAPR-TC12 datasets demonstrate the superior performance of ACHFCA to state-of-the-art hashing approaches.