Yuan FANG, Ph.D.
Assistant Professor of Computer Science
School of Computing and Information Systems
Singapore Management University
Office: SCIS1 Room 4051
Email: yfang "at" smu.edu.sg
Short Biography
Since July 2018, I have been an Assistant Professor at the School of Computing and Information Systems, Singapore Management University (SMU). Prior to joining SMU, I was a data scientist at DBS Bank, and a research scientist at A*STAR. I obtained a PhD Degree in Computer Science from the University of Illinois at Urbana-Champaign in 2014 on a fully funded scholarship from A*STAR, and Bachelor of Computing with First Class Honors from National University of Singapore in 2009 as the top student in Computer Science.
Research Interests
My general interest lies in the broad areas of data mining, machine learning and artificial intelligence. More specifically, I am working on the following research topics: (1) Learning on graphs and information networks; (2) Web and social media analytics; (3) Recommendation systems; (4) Application of knowledge graphs on data mining problems. More details can be found in my research statement, the projects page, and the publications page.
News
[09/2024] We have three papers accepted by EMNLP 2024, on adapter tuning for few-shot relation learning on knowledge graphs, out-of-scope intent classification (Findings), and a survey on ontology expansion for conversational understanding.
[07/2024] We have two papers accepted by IEEE TKDE, on generalized graph prompt [PDF] and prompt tuning for text-attributed graphs [PDF].
[07/2024] We have a paper accepted by CIKM 2024, on large language models for recommendation [PDF].
[05/2024] We have a paper accepted by KDD 2024, on geodesic distance-based augmentation on graphs [PDF].
[05/2024] We have a paper accepted by ACL Findings 2024, on parameter-efficient fine-tuning [PDF].
[05/2024] We organized a tutorial titled "Towards Graph Foundation Models" [Part I, Part II & Part III] at WWW 2024 held in Singapore.
[05/2024] Our paper on GraphPrompt [PDF] ranks among the Top 5 Most Influential Papers in WWW'23 by Paper Digest (2024-05 Version).
[04/2024] We have two papers accepted by IJCAI 2024, on general graph matching [PDF], and heterogeneous graph transformer [PDF].
[01/2024] We have three papers accepted by WWW 2024, on multi-task graph prompt [PDF], simple transformer for dynamic graphs [PDF], and diffusion-based negative sampling on graphs [PDF].
[01/2024] I am giving a talk "Would prompt work for graph learning? An exploration of few-shot learning on graphs" [Slides] at VALSE Webinar Series.
[12/2023] We have a paper accepted by AAAI 2023, on heterogeneous graph prompt [PDF].
[09/2023] We have two papers accepted by NeurIPS 2023, on propensity estimation for causal recommendation [PDF] and spectral graph contrastive learning [PDF].
[09/2023] I am giving a keynote talk "Low-Resource Learning on Graphs" [Slides] at the International Workshop on Deep Learning Practice for High-Dimensional Sparse Data, collocated with ACM RecSys 2023 held in Singapore.
[08/2023] We have a paper accepted by TKDE, on learning tail node embeddings [PDF].
[08/2023] We have an applied research paper accepted by CIKM 2023, on voucher abuse detection [PDF], in collaboration with Lazada Group.