I'm now a fourth-year PhD candidate at the National University of Singapore supervised by Prof. Dong Jin Song. I received my Bachelor from Fudan University in 2016.

My research interests lie in robust and trustworthy machine learning techniques. Recently I am interested in AI Agent and LLM.

I'm open to discussion or collaboration. Feel free to drop me an email if you're interested in my research.

[CV] | [Google Scholar] | [GitHub] | [LinkedIn]
RECENT NEWS 🧅
  • 01/2024. I become a research intern at Lenovo working on AI Agent!
  • 11/2023. I was honored to receive the Dean’s Graduate Award from NUS. Thanks Prof. Dong for the nomination and support!
  • 07/2023. Our paper DeepDebugger: An Interactive Time-Travelling Debugging Approach for Deep Classifiers has been accepted to ESEC/FSE 2023!
  • 05/2023. Our paper Thompson Sampling with Less Exploration is Fast and Optimal has been accepted to ICML 2023!
  • 09/2022. Our paper Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective has been accepted to NeurIPS 2022!
  • 04/2022. Our paper Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training has been accepted to IJCAI 2022!
  • 03/2022. Our paper Inferring Phishing Intention via Webpage Appearance and Dynamics: A Deep Vision Based Approach has been accepted to USENIX 2022!
  • 02/2022. Our paper DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training has been accepted to AAAI22 with oral presentation (4%)!
PUBLICATIONS
  • [new] Xianglin Yang, Yun Lin, Yifan Zhang, Linpeng Huang, Jin Song Dong, Hong Mei.
    DeepDebugger: An Interactive Time-Travelling Debugging Approach for Deep Classifiers. ESEC/FSE 2023 .
  • Tianyuan Jin, Xianglin Yang, Xiaokui Xiao, Pan Xu.
    Thompson Sampling with Less Exploration is Fast and Optimal. ICML 2023 .
  • Ruofan Liu, Yun Lin, Xianglin Yang, Jin Song Dong.
    Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective. NeurIPS 2022 .
  • Xianglin Yang, Yun Lin, Ruofan Liu, Jin Song Dong.
    Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training. IJCAI 2022 . [code] [website]
  • Ruofan Liu, Yun Lin, Xianglin Yang, Siang Hwee Ng, Dinil Mon Divakaran, Jin Song Dong.
    Inferring Phishing Intention via Webpage Appearance and Dynamics: A Deep Vision Based Approach. USENIX Security 2022 . [code] [website]
  • Xianglin Yang#, Yun Lin#, Ruofan Liu, Zhenfeng He, Chao Wang, Jin Song Dong, and Hong Mei.
    DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training. AAAI 2022. [oral presentation, 4.5%]. [paper] [video] [code] [website]

    Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as active learning, and track the root cause of unexpected training results such as performance degeneration. In this work, we propose a time-travelling visual solution DeepVisualInsight (DVI), aiming to manifest the spatio-temporal causality while training a deep learning image classifier. The spatio-temporal causality demonstrates how the gradient-descent algorithm and various training data sampling techniques can influence and reshape the layout of learnt input representation and the classification boundaries in consecutive epochs. Such causality allows us to observe and analyze the whole learning process in the visible low dimensional space. Technically, we propose four spatial and temporal properties and design our visualization solution to satisfy them. These properties preserve the most important information when (inverse-)projecting input samples between the visible low-dimensional and the invisible high-dimensional space, for causal analyses. Our extensive experiments show that, comparing to baseline approaches, we achieve the best visualization performance regarding the spatial/temporal properties and visualization efficiency. Moreover, our case study shows that our visual solution can well reflect the characteristics of various training scenarios, showing good potential of DVI as a debugging tool for analyzing deep learning training processes.

WORKING EXPERIENCE
EDUCATION
AWARDS
CONTACT

Computing 2,
15 Computing Drive, National University of Singapore,
Singapore, 117418

Email: xianglin[at]u[dot]nus[dot]edu

© 2022 YANG Xianglin | Powered by Skeleton and Jiarui Gan's template | Updated 2022-05-16