Yuankai Luo

Email: luoyk@buaa.edu.cn

I am a third-year PhD student in School of Computer Science and Engineering, Beihang University, supervised by Prof. Lei Shi and a visiting student at The Hong Kong Polytechnic University under the supervision of Prof. Xiao-Ming Wu. Concurrently, I do research supervised by Veronika Thost. Previously, I received the BEng degree in Computer Science and Engineering from Chongqing University of Posts and Telecommunications, in 2021.

My research interests include Graph Learning, Graph Neural Networks, etc.

news

Dec 20, 2023	I was grateful to be awarded the 2023 Computer Star (Star of Science and Technology), Beihang University.
Sep 22, 2023	Two first-author papers are accepted by NeurIPS 2023.
Jun 21, 2023	I passed my PhD qualify exam.
May 17, 2023	One first-author paper is accepted by KDD 2023.
Sep 8, 2022	One first-student-author paper is accepted by ACM TIST.

selected publications

Transformers over Directed Acyclic Graphs

Yuankai Luo, Veronika Thost, and Lei Shi

In Thirty-seventh Conference on Neural Information Processing Systems, 2023

PDF Code Poster Slides Website
Improving Self-supervised Molecular Representation Learning using Persistent Homology

Yuankai Luo, Lei Shi, and Veronika Thost

In Thirty-seventh Conference on Neural Information Processing Systems, 2023

PDF Code Poster Slides Website
Impact-Oriented Contextual Scholar Profiling Using Self-Citation Graphs

Yuankai Luo, Lei Shi, Mufan Xu, and 4 more authors

In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

Abs arXiv Website

Quantitatively profiling a scholar’s scientific impact is important to modern research society. Current practices with bibliometric indicators (e.g., h-index), lists, and networks perform well at scholar ranking, but do not provide structured context for scholar-centric, analytical tasks such as profile reasoning and understanding. This work presents GeneticFlow (GF), a suite of novel graph-based scholar profiles that fulfill three essential requirements: structured-context, scholar-centric, and evolution-rich. We propose a framework to compute GF over large-scale academic data sources with millions of scholars. The framework encompasses a new unsupervised advisor-advisee detection algorithm, a well-engineered citation type classifier using interpretable features, and a fine-tuned graph neural network (GNN) model. Evaluations are conducted on the real-world task of scientific award inference. Experiment outcomes show that the F1 score of best GF profile significantly outperforms alternative methods of impact indicators and bibliometric networks in all the 6 computer science fields considered. Moreover, the core GF profiles, with 63.6%sim66.5% nodes and 12.5%sim29.9% edges of the full profile, still significantly outrun existing methods in 5 out of 6 fields studied. Visualization of GF profiling result also reveals human explainable patterns for high-impact scholars.
Transformers for Capturing Multi-level Graph Structure using Hierarchical Distances

Yuankai Luo

2023

arXiv