Le Yu (于乐)’s Homepage
Brief Bio
I am currently a fifth-year computer science Ph.D. student in the School of Computer Science and Engineering at Beihang University, supervised by Prof. Weifeng Lv. I received the B.S. degree in the School of Computer Science and Engineering at Beihang University in 2019.
Spatio-temporal graphs can abstractly represent most things in reality. I devote myself to designing neural networks for representation learning on spatio-temporal graphs, and using the learned representations to empower various scenarios. My research interests include (spatio-temporal) graph neural networks, language models, recommender systems, traffic forecasting, et al. I am strongly self-motivated and aim to pursue cutting-edge AI research. I have published several peer-reviewed papers in top venues such as NeurIPS, KDD, WWW, IEEE TKDE, EMNLP, AAAI, and IJCAI. I have also served as a PC member/reviewer for conferences/journals like AAAI, LOG, TOIS, TKDD, TNNLS, and Neural Networks.
Currently, I am interested in pursuing two main research directions.
- Explore the alignment of language models by studying the properties of their parameters. This includes
- identifying and extracting key parameters that determine the success of Supervised Fine-Tuning (SFT);
- controlling the roles of parameters during SFT for better interpretability;
- developing new SFT methods to build general language models that can handle various NLP tasks.
- Design domain-specific (large) language models that can cover fields like spatio-temporal graph networks and recommender systems. This involves
- incorporating domain-specific and factual knowledge into language models;
- developing language models to capture dynamics and topologies in graphs;
- encoding user information to obtain personalized language models.
Now, I am looking for a postdoctoral position (starting in 2024). Please contact me by email at yule@buaa.edu.cn if interested.
News
[10/2023] One paper was accepted by Findings of EMNLP 2023. Thanks to all my collaborators!
[09/2023] One paper was accepted by NeurIPS 2023. Thanks to all my collaborators!
[08/2023] Two papers were accepted by IEEE TKDE. Thanks to all my collaborators!
[04/2023] One paper was accepted by IJCAI 2023. Thanks to all my collaborators!
[12/2022] One paper was accepted by IEEE TKDE. Thanks to all my collaborators!
[11/2022] One paper was accepted by AAAI 2023. Thanks to all my collaborators!
[03/2022] One paper was accepted by IEEE TKDE. Thanks to all my collaborators!
[01/2022] One paper was accepted by WWW 2022. Thanks to all my collaborators!
[01/2022] One paper was accepted by Knowledge-Based Systems. Thanks to all my collaborators!
[04/2021] One paper was accepted by Knowledge-Based Systems. Thanks to all my collaborators!
[09/2020] One paper was accepted by Neurocomputing. Thanks to all my collaborators!
[05/2020] One paper was accepted by KDD 2020. Thanks to all my collaborators!
Publications
In the Year of 2023
[arXiv1] Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li. Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch. arXiv 2023. Paper Code
[C1] Tao Zou*, Le Yu*, Yifei Huang, Leilei Sun, Bowen Du. Pretraining Language Models with Text-Attributed Heterogeneous Graphs. EMNLP 2023 (Findings). Paper Code
[C2] Le Yu, Leilei Sun, Bowen Du, Weifeng Lv. Towards Better Dynamic Graph Learning: New Architecture and Unified Library. NeurIPS 2023 (Poster). Paper Code
[arXiv2] Le Yu. An Empirical Evaluation of Temporal Graph Benchmark. arXiv 2023. Paper Code
[C3] Le Yu, Zihang Liu, Tongyu Zhu, Leilei Sun, Bowen Du, Weifeng Lv. Predicting Temporal Sets with Simplified Fully Connected Networks. AAAI 2023 (Oral). Paper Code
[C4] Xiaodong Lu, Shuo Ji, Le Yu, Leilei Sun, Bowen Du, Tongyu Zhu. Continuous-Time Graph Learning for Cascade Popularity Prediction. IJCAI 2023. Paper Code
[J1] Le Yu, Zihang Liu, Leilei Sun, Bowen Du, Chuanren Liu, Weifeng Lv. Continuous-Time User Preference Modelling for Temporal Sets Prediction. IEEE TKDE. Paper Code
[J2] Tao Zou, Le Yu, Leilei Sun, Bowen Du, Deqing Wang, Fuzhen Zhuang. Event-based Dynamic Graph Representation Learning for Patent Application Trend Prediction. IEEE TKDE. Paper Code
[arXiv3] Tao Zou, Le Yu, Leilei Sun, Bowen Du, Deqing Wang, Fuzhen Zhuang. Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent Classification. arXiv 2023. Paper Code
[arXiv4] Zihang Liu, Le Yu, Tongyu Zhu, Leiei Sun. A Simple Framework for Multi-mode Spatial-Temporal Data Modeling. arXiv 2023. Paper Code
In the Year of 2022
[C1] Le Yu, Guanghui Wu, Leilei Sun, Bowen Du, Weifeng Lv. Element-guided Temporal Graph Representation Learning for Temporal Sets Prediction. Proceedings of the ACM Web Conference 2022 (WWW 2022). Paper Code
[J1] Le Yu, Leilei Sun, Bowen Du, Tongyu Zhu, Weifeng Lv. Label-Enhanced Graph Neural Network for Semi-supervised Node Classification. IEEE TKDE. Paper Code
[J2] Le Yu, Leilei Sun, Bowen Du, Chuanren Liu, Weifeng Lv, Hui Xiong. Heterogeneous Graph Representation Learning with Relation Awareness. IEEE TKDE. Paper Code
[J3] Xuxiang Ta, Zihan Liu, Xiao Hu, Le Yu, Leilei Sun, Bowen Du. Adaptive Spatio-temporal Graph Neural Network for Traffic Forecasting. Knowledge-Based Systems. Paper Code
In the Year of 2021
[J1] Nannan Shi, Le Yu, Leilei Sun, Lihua Wang, Chunming Lin, Ruixing Zhang. Deep Heterogeneous Network for Temporal Set Prediction. Knowledge-Based Systems. Paper Code
In the Year of 2020
[C1] Le Yu, Leilei Sun, Bowen Du, Chuanren Liu, Hui Xiong, Weifeng Lv. Predicting Temporal Sets with Deep Neural Networks. (KDD 2020). Paper Code
[J1] Le Yu, Bowen Du, Xiao Hu, Leilei Sun, Liangzhe Han, Weifeng Lv. Deep Spatio-temporal Graph Convolutional Network for Traffic Accident Prediction. Neurocomputing. Paper Code
[arXiv1] Le Yu, Leilei Sun, Bowen Du, Chuanren Liu, Weifeng Lv, Hui Xiong. Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning. arXiv 2020. Paper Code
Education
- Sept. 2019 - now. Ph.D. student, School of Computer Science and Engineering, Beihang University
Supervisor: Prof. Weifeng Lv - Sept. 2015 - Jun. 2019 B.S., School of Computer Science and Engineering, Beihang University
Honors Awarded
- 2020 & 2023 National Scholarship for Graduate Students, Beihang University
- 2023 Huawei Scholarship, Beihang University
- 2023 Guorui Scholarship, Beihang University
- 2019 Graduate Freshman Scholarship, Beihang University
- Merit Student & Outstanding Graduate Student (2020, 2022, 2023), Beihang University
Invited Talks
- Predicting Temporal Sets with Deep Neural Networks
– The 18th China Symposium on Machine Learning and Applications (MLA’20) at Nov. 8th, 2020
Professional Services
PC Member (or Reviewer):
AAAI 2023, 2024; LOG 2022, 2023; ACM TOIS; ACM TKDD; IEEE TNNLS; Neural NetworksAssistant PC Member (or Reviewer):
SIGIR 2020, 2021, 2022, 2023; KDD 2020, 2021, 2022, 2023; AAAI 2020, 2021, 2022; IJCAI 2021, 2022, 2023; CIKM 2020, 2021; ICDM 2021; WSDM 2021, 2022; IEEE TKDE; IEEE TITS; ACM TIST; Neurocomputing; Knowledge-Based Systems
Experiences
- Jun. 2023 - now., Research Intern, DAMO Academy, Alibaba Group