Hefu Zhang

ORCID: 0000-0003-1881-3192
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • FinTech, Crowdfunding, Digital Finance
  • Microfinance and Financial Inclusion
  • Blockchain Technology Applications and Security
  • Advanced Graph Neural Networks
  • Health and Medical Research Impacts
  • Caching and Content Delivery
  • Machine Learning and Algorithms
  • Industrial Gas Emission Control
  • Sharing Economy and Platforms
  • Domain Adaptation and Few-Shot Learning
  • Internet Traffic Analysis and Secure E-voting
  • Complex Network Analysis Techniques
  • scientometrics and bibliometrics research
  • Maritime Transport Emissions and Efficiency
  • Catalytic Processes in Materials Science
  • Recommender Systems and Techniques

University of Science and Technology of China
2017-2024

Harbin Engineering University
2015

P2P lending is an emerging Internet-based application where individuals can directly borrow money from each other. The past decade has witnessed the rapid development and prevalence of online platforms, examples which include Prosper, LendingClub, Kiva. Meanwhile, extensive research been done that mainly focuses on studies platform mechanisms transaction data. In this article, we provide a comprehensive survey about lending, which, to best our knowledge, first focused effort in field....

10.1145/3078848 article EN ACM Transactions on Intelligent Systems and Technology 2017-07-24

Crowdfunding is an emerging Internet fundraising mechanism by raising monetary contributions from the crowd for projects or ventures. In these platforms, dynamics, i.e., daily funding amount on campaigns and perks (backing options with rewards), are most concerned issue creators, backers platforms. However, tracking dynamics in crowdfunding very challenging still under-explored. To that end, this paper, we present a focused study important problem. A special goal to forecast given campaign...

10.1145/3097983.3098030 article EN 2017-08-04

Social network embedding, namely, embedding social nodes into a low-dimensional space, is the foundation of analysis, such as node classification and link prediction. Although many existing methods attempt to address this task, most them only consider shallow relationship between two in network, which ignore capturing multiple semantic-rich relationships users. To end, we define multi-path relationships, propose preserved method named MPR-SNE, based on recurrent neural framework that...

10.1109/access.2019.2900920 article EN cc-by-nc-nd IEEE Access 2019-01-01

Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but still under exploration. Existing studies either fit fluctuations time-series or employ regularization terms to constrain learned tendencies. However, few them take into account inherent decision-making process between investors and dynamics. To address problem, paper, we propose Trajectory-based Continuous Control for Crowdfunding (TC3)...

10.1609/aaai.v34i04.6087 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2020-04-03

The present paper investigates the simultaneous removal and synergistic effect of SO2 NOx in natrium-alkali solutions a countercurrent packed column continuous flow mode. On basis high efficiency, efficiencies under different process variables such as concentration, reaction temperature, initial pH value, oxidation degree additive were investigated. mechanism for based on method deduced. efficiency was about 100%, but denitration complex. In this paper, optimal conditions determined....

10.1252/jcej.14we3600 article EN JOURNAL OF CHEMICAL ENGINEERING OF JAPAN 2015-01-01

Knowledge discovery and utilization are two essential cognitive processes that enable humans to understand the world extract new insights from their surroundings. These have motivated machine learning studies, particularly zero-shot (ZS), which seeks identify unseen concepts through use of side information. Previous ZS studies primarily focused on utilizing existing knowledge infer events, yet they overlook crucial process integrated modeling these knowledge-aware processes. In this study,...

10.1145/3700444 article EN ACM Transactions on Knowledge Discovery from Data 2024-10-12

Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but still under exploration. Existing studies either fit fluctuations time-series or employ regularization terms to constrain learned tendencies. However, few them take into account inherent decision-making process between investors and dynamics. To address problem, paper, we propose Trajectory-based Continuous Control for Crowdfunding (TC3)...

10.48550/arxiv.1912.12016 preprint EN other-oa arXiv (Cornell University) 2019-01-01
Coming Soon ...