Wenjie Feng
Scholar

Wenjie Feng

Google Scholar ID: EV1kntYAAAAJ
University of Science and Technology of China
Data MiningGraph LearningTrustworthy AIMachine learningSafety
Citations & Impact
All-time
Citations
2,246
 
H-index
9
 
i10-index
9
 
Publications
20
 
Co-authors
14
list available
Resume (English only)
Academic Achievements
  • Paper “FAVDisco: Modeling and Discovering File Access Vulnerabilities” accepted to TOSEM 2025
  • Paper “Rethinking Machine Unlearning in Image Generation Models” accepted to CCS 2025
  • Paper “Interrelated Dense Subgraph Detection in Multilayer Networks” accepted to ICDE 2025
  • Paper “ID3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition” accepted to NeurIPS 2024
  • Paper “One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity” accepted to ACM MM 2024
  • Paper “Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks” accepted to NAACL 2024
  • Paper “Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering” accepted to ICML 2023
  • Paper “Unified Dense Subgraph Detection: Fast Spectral Theory based Algorithms” accepted to IEEE TKDE
  • Demo & poster paper “EasySpider: Visual Code-Free Web Crawler/Spider” accepted to The WebConf 2023 (March 2023)
  • Paper “Hierarchical Dense Pattern Detection in Tensors” accepted to TKDD
  • Publications in top venues including ICML, NeurIPS, ICDE, WWW, ACM MM, TKDE, TKDD, and TOSEM
Background
  • Professor at the School of Artificial Intelligence and Data Science, University of Science and Technology of China (USTC)
  • Research focuses on large-scale data mining, trustworthy and secure AI & systems
  • Emphasizes machine learning techniques and real-world applications, including graph mining and learning, ML privacy, foundation models, FinTech, and learning systems
  • Serves as a program committee member for top-tier conferences such as ICML, CVPR, WWW, SIGKDD, NeurIPS, and IJCAI
  • Acts as a reviewer for prestigious journals including TKDE, TDSC, TKDD, KAIS, and TNNLS