Coder Social home page Coder Social logo

Welcome to Xingzhi (Jacky) Guo's Homepage

Me in 2018, an unknown street in Manhattan Something about me
drawing My name is Xingzhi (Jacky) Guo (ιƒ­,θ‘ŒδΉ‹).
I was born and raised in Lanxi.
It's a charming tiny town, east-central China
I spent 7 years in Taiwan πŸŽ“πŸ₯ŸπŸ§‹πŸ€€
Finished PhD in Long Island, New York πŸ—½πŸŒ†.
Now working at Amazon in Bellevue, WA 🏞🌧 .

Research Interests

Graph representation learning, Deep learning applications for NLP/Dialogue Agent, Optimization

Education

  • Ph.D. in Computer Science, 2018.8 - 2023.5
    GPA 4.0/4.0; Supervised by Prof.Steven Skiena @Data Science Lab, Stony Brook University, New York
  • M.S. in Computer Science and Information Engineering, 2015.9 - 2018.7
    GPA 3.9/4.0; Supervised by Prof.Li-Chen Fu @Intelligent Robot Lab, National Taiwan University, Taiwan
  • B.S. in Telecommunication and Information Engineering, 2011.9 - 2015.7
    GPA 3.9/4.0; Supervised by Prof.Shu-Yin Chiang @Robotics Research Center, Ming Chuan University, Taiwan

Work Experience

  • Applied Scientist (Full-time), 2023.7 - present
    @Artificial General Intelligence (previously Alexa AI), Amazon, Bellevue, WA
    • Topics: LLM for Proactive Agent and RecSys
  • Applied Scientist (Intern), Summer 2019/2020/2021/2022
    @Alexa AI, Amazon, Seattle, WA
    • Topics: Dialogue directedness classification, Active learning, Pretraining (L)LM, Non-autoregressive (L)LM

Academic Service

  • Program Committee LoG2023, KDD2022/23, CIKM2023, PAKDD2023/24, ICWSM2022/23

Publications

  • Guo X., Handzlik D, Jones JJ., Skiena S., The Evolution of Occupational Identity in Twitter Biographies, The International AAAI Conference on Web and Social Media (ICWSM) 2024 (Long)
    • We collect and analyze the biography changes of 50 million Twitter users from 2015 to 2021, using their bios as a proxy for self-identity, with a focus on work identity.
  • Zhang C., Xiang W., Guo X., Zhou B., Yang D., SubAnom: Efficient Subgraph Anomaly Detection Framework over Dynamic Graphs, Workshop of Graph Learning on Graphs (MLoG) at The IEEE International Conference on Data Mining (ICDM) 2023.
  • Chen Z., Guo X., Zhou B.*, Yang D., Skiena S., Accelerating Personalized PageRank Vector Computation, ACM Knowledge Discovery and Data Mining (KDD)2023 (Long)
    • Make faster PPR approximation by introducing theoretically justifiable three-line change. *:corresponding author
  • Borca-Tasciuc G., Guo X., Bak S., Skiena S., Provable Fairness for Neural Network Models using Formal Verification, European Workshop on Algorithmic Fairness 2023 (Short)
    • Proposed fairness metrics using Formal Verification to evaluate the neural classifiers' fairness without any testing data sample
  • Lin Z., Feng L., Guo X., Yin R., Kwoh CK., C Xu. "COMET: Convolutional Dimension Interaction for Deep Matrix Factorization." ACM Transactions on Intelligent Systems and Technology(2023)
  • Sultan SF., Guo X., Skiena S., Low-Dimensional Genotype Embeddings for Predictive Models, ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) 2022 (Short)
    • Embed ~100K-dimensional SNPs of human chromosomes to a few hundreds dimensions while preserving predictive power and privacy. 🧬
  • Guo X., Zhou B., Skiena S., Subset Node Anomaly Tracking over Large Dynamic Graphs. ACM Knowledge Discovery and Data Mining (KDD)2022 (Long)
    • Fast algorithm to track both subset node/graph-level anomalies over large dynamic weighted graphs 😎
  • Guo X., Kondracki B., Nikiforakis N., S., Skiena S., Verba Volant, Scripta Volant: Understanding Post-publication Title Changes in News Outlets, ACM Web Conference (WWW) 2022 (Long)
    • A cute investigation about why/how news agencies did post-publication modification πŸ˜€
  • Guo X., Zhou B., Skiena S., Subset Node Representation Learning over Large Dynamic Graphs. ACM Knowledge Discovery and Data Mining (KDD)2021 (Long)
    • A very cool, useful non-deep fast learning algorithm for semi-novel practical graph learning problem 😎
  • K Gillespie, I.C. Konstantakopoulos, Guo X., Vasudevan VT., and Sethy A. "Improving device directedness classification of utterances with semantic lexical features." Speech, & Signal Processing (ICASSP)2020 (Short)
    • Detect whether the user is talking to Alexa. From my first internship, thanks to all teammates 🍻!
  • Guo X., Huang Y., Gamborino E., Tseng SH., Fu LC., and Yeh SL., "Inferring human feelings and desires for human-robot trust promotion." International Conference on Human-Computer Interaction (HCII)2019 (Long)
    • Promoting human-robot trust by identifying human desire in conversations. Part of my master thesis. Missing Taipei so much πŸ§‹
  • Chiang SY., Guo X., and Hu HW., "Real time self-localization of omni-vision robot by pattern match system." International Conference on Advanced Robotics and Intelligent Systems (ARIS) 2014 (Short)
    • My very first paper when I was an undergrad, and devoted almost entire 3 years in making a team of cool robots from scratch (both software/hardware)More Video πŸ€–πŸ€©

Manuscripts in Submission

  • Guo X., Zhou B., Chen H., Verstyuk S., Skiena S., Submitted to The Proceedings of the National Academy of Sciences (PNAS)
  • Guo X., Zhou B., Skiena S., plan to submit to KDD'24
  • Guo X., Skiena S., Hierarchies over Vector Space: Orienting Word and Graph Embeddings (A small cute idea, in submission)

Presentations

Xingzhi's Projects

colossalai icon colossalai

Making large AI models cheaper, faster and more accessible

dsp icon dsp

𝗗𝗦𝗣: Demonstrate-Search-Predict. A framework for composing retrieval and language models for knowledge-intensive NLP.

dynamicppe icon dynamicppe

Code for the KDD21 paper "Subset Node Representation Learning over Large Dynamic Graphs"

dynanom icon dynanom

Codebase for KDD22 paper "Subset Node Anomaly Tracking over Large Dynamic Graphs"

gpt4all icon gpt4all

gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue

instantgnn icon instantgnn

Instant Graph Neural Networks for Dynamic Graphs

pprgo_pytorch icon pprgo_pytorch

PPRGo model in PyTorch, as proposed in "Scaling Graph Neural Networks with Approximate PageRank" (KDD 2020)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.