Scholar
Longlong Lin
Google Scholar ID: TgqGrv3_ytYC
Southwest University
Citations & Impact
Citations
191
H-index
9
i10-index
7
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- His work has been published in several CCF-A conferences and journals, including SIGMOD, VLDB, ICDE, KDD, TKDE, AAAI, PPoPP, ASPLOS, and DAC. Some notable publications are:
- - DTMiner: A Data-centric System for Efficient Temporal Motif Mining (PPoPP 2026)
- - NCSAC: Effective Neural Community Search via Attribute-augmented Conductance (TKDE 2026)
- - Pseudoarboricity-Based Skyline Important Community Search in Large Networks (TKDE 2026)
- - Theoretically and Practically Efficient Resistance Distance Computation on Large Graphs (VLDB 2026)
- - GDBA: Defending Graph Neural Networks via Attribute Debiasing (Expert Systems With Applications 2026)
- - One Index for All: Towards Efficient Personalized PageRank Computation for Every Damping Factor (SIGMOD 2026)
Research Experience
- Currently an Associate Professor at Southwest University, College of Computer and Information Science.
Education
- Received a Ph.D. from Huazhong University of Science and Technology (HUST) in 2022, advised by Prof. Pingpeng Yuan and Prof. Dongxiao Yu. Co-supervised by Prof. Rong-Hua Li from Beijing Institute of Technology since 2018.
Background
- Research interests include LLM-based Text Attribute Graph Analysis, Graph Machine Learning, Graph Clustering, and Similarity Search. Focuses on enhancing the performance of large models through Graph Retrieval Augmented Generation (RAG), as well as scalability, temporality, robustness, and graph augmentation.
Miscellany
- Plans to recruit 3-5 master's students annually, welcoming applications from students who have passed the entrance exam or are recommended. Also, continuously recruiting freshmen/sophomores for research training, with the goal of developing research methodologies, aiming for CCF B/Chinese Academy of Sciences Zone 1 publications. Outstanding undergraduate and graduate students can be recommended for internships at companies like Alibaba and Huawei, or further studies at top universities.
Co-authors