activity
20202023
most citedSubset Node Anomaly Tracking over Large Dynamic Graphs

22 citations · 36 across the 5 of their papers we have counts for

collaborators

6 papers

cs.DS2023

Accelerating Personalized PageRank Vector Computation

Zhen Chen, Xingzhi Guo, Baojian Zhou +2

Personalized PageRank Vectors are widely used as fundamental graph-learning tools for detecting anomalous spammers, learning graph embeddings, and training graph neural networks. T…

cs.LG2022★ 3 cited

Provable Fairness for Neural Network Models using Formal Verification

Giorgian Borca-Tasciuc, Xingzhi Guo, Stanley Bak +1

Machine learning models are increasingly deployed for critical decision-making tasks, making it important to verify that they do not contain gender or racial biases picked up from…

cs.CL2022

Hierarchies over Vector Space: Orienting Word and Graph Embeddings

Xingzhi Guo, Steven Skiena

Word and graph embeddings are widely used in deep learning applications. We present a data structure that captures inherent hierarchical properties from an unordered flat embedding…

cs.SI2022★ 22 cited

Subset Node Anomaly Tracking over Large Dynamic Graphs

Xingzhi Guo, Baojian Zhou, Steven Skiena

Tracking a targeted subset of nodes in an evolving graph is important for many real-world applications. Existing methods typically focus on identifying anomalous edges or finding a…

eess.AS2020★ 11 cited

Improving Device Directedness Classification of Utterances with Semantic Lexical Features

Kellen Gillespie, Ioannis C. Konstantakopoulos, Xingzhi Guo +2

User interactions with personal assistants like Alexa, Google Home and Siri are typically initiated by a wake term or wakeword. Several personal assistants feature "follow-up" mode…

cs.IR2020

COMET: Convolutional Dimension Interaction for Collaborative Filtering

Zhuoyi Lin, Lei Feng, Xingzhi Guo +4

Representation learning-based recommendation models play a dominant role among recommendation techniques. However, most of the existing methods assume both historical interactions…