Dong Li

Dong Li

Auto-generated profile, based on publicly available information

Dong Li

Kent State University, Kent, USA

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
7 March 2024 in ACM Transactions on Recommender Systems
Verified
Journal Article
Open access
DLDong Li
Dong Li
RJRuoming Jin
Ruoming Jin
ZLZhenming Liu
Zhenming Liu
BRBin Ren
Bin Ren
JGJing Gao
Jing Gao
ZLZhi Liu
Zhi Liu
Personalized recommender systems play a crucial role in modern society, especially in e-commerce, news, and ads areas. Correctly evaluating and comparing candidate recommendation models is as essential as constructing ones. The common offline evaluation strategy is holding out some user-interacted items from training data and evaluating the performance of recommendation models based on how many items they can retrieve. Specifically, for any hold-out item or so-called target item for a user, the recommendation models try to predict the probability that the user would interact with the item and rank it among overall items, which is called global evaluation . Intuitively, a good recommendation model would assign high probabilities to such hold-out/target items. Based on the specific ranks, some metrics like Recall@K and NDCG@K can be calculated to further quantify the quality of the recommender model. Instead of ranking the target items among all items, Koren first proposed to rank them among a small sampled set of items , then quantified the performance of the models, which is called sampling evaluation . Ever since then, there has been a large amount of work adopting sampling evaluation due to its efficiency and frugality. In recent work, Rendle and Krichene argued that the sampling evaluation is “inconsistent” with respect to a global evaluation in terms of offline top- K metrics. In this work, we first investigate the “inconsistent” phenomenon by taking a glance at the connections between sampling evaluation and global evaluation. We reveal the approximately linear relationship between sampling with respect to its global counterpart in terms of the top- K Recall metric. Second, we propose a new statistical perspective of the sampling evaluation—to estimate the global rank distribution of the entire population. After the estimated rank distribution is obtained, the approximation of the global metric can be further derived. Third, we extend the work of Krichene and Rendle, directly optimizing the error with ground truth, providing not only a comprehensive empirical study but also a rigorous theoretical understanding of the proposed metric estimators. To address the “blind spot” issue, where accurately estimating metrics for small top- K values in sampling evaluation is challenging, we propose a novel adaptive sampling method that generalizes the expectation-maximization algorithm to this setting. Last but not least, we also study the user sampling evaluation effect. This series of works outlines a clear roadmap for sampling evaluation and establishes a foundational theoretical framework. Extensive empirical studies validate the reliability of the sampling methods presented.

1 May 2010
Verified
Conference Paper
Closed access
DLDong Li
Dong Li
YWYuhao Wang
Yuhao Wang
LHLinli Hu
Linli Hu
JLJing Li
Jing Li
XGXuezhao Guo
Xuezhao Guo
JLJie Liu
Jie Liu
Passenger line flow in China is so huge that current ticketing systems cannot be viewed optimistic. After pointing out the disadvantages of existing telephone and web network ticketing systems and further comparing barcode, two-dimensional barcode and RFID(Radio Frequency Identification), this paper proposed a new ticketing system based on C/S architecture and two-dimensional(2-D) barcode on mobile phone so as to alleviate the pressure caused by the huge passenger line flow, and to provide a fair, convenient and secure ticketing system. There are also presentations of framework structure, module function and class designing in this paper.

1 July 2022
Verified
Conference Paper
Open access
YCYinan Chen
Yinan Chen
ZGZhuanming Gao
Zhuanming Gao
DLDong Li
Dong Li

1 January 2012
Verified
Conference Paper
Closed access
YFYanfang Fan
Yanfang Fan
DLDong Li
Dong Li
YXYongqiang Xie
Yongqiang Xie
Bo XuBo Xu
Bo Xu
Haifei WangHaifei Wang
Haifei Wang
With the heterogeneous threats of network ongoing, the problems of network security become more and more intractable, besides, the compatibility issues of security protection-equipments are emerging in endlessly. Thus, the unified treat management has been a research hotpot currently. In this paper, based on analyzing the status quo of UTM (unified treat management), as well as the performance detects of related equipments, we present the NAC-UTM, a holistic protection scheme of intranet, which combines UTM with technology of network access control. The emphasis of our research is to illustrate the operating principle of UTM-NAC scheme, and then we verify the superiority of this scheme with a simplified experiment. The test result indicates that our solution could greatly promote performance of UTM equipments.