111 citations · 331 across the 27 of their papers we have counts for
29 papers
Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching
Tim Kaler, Alexandros-Stavros Iliopoulos, Philip Murzynowski +3
Training and inference with graph neural networks (GNNs) on massive graphs has been actively studied since the inception of GNNs, owing to the widespread use and success of GNNs in…
GUAP: Graph Universal Attack Through Adversarial Patching
Xiao Zang, Jie Chen, Bo Yuan
Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversar…
Bridging Mean-Field Games and Normalizing Flows with Trajectory Regularization
Han Huang, Jiajia Yu, Jie Chen +1
Mean-field games (MFGs) are a modeling framework for systems with a large number of interacting agents. They have applications in economics, finance, and game theory. Normalizing f…
Attacking c-MARL More Effectively: A Data Driven Approach
Nhan H. Pham, Lam M. Nguyen, Jie Chen +3
In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial…
Memory-based Message Passing: Decoupling the Message for Propogation from Discrimination
Jie Chen, Weiqi Liu, Jian Pu
Message passing is a fundamental procedure for graph neural networks in the field of graph representation learning. Based on the homophily assumption, the current message passing a…
Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification
Shaojie Xu, Joel Vaughan, Jie Chen +2
Although neural networks (NNs) with ReLU activation functions have found success in a wide range of applications, their adoption in risk-sensitive settings has been limited by the…
Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
Tim Kaler, Nickolas Stathas, Anne Ouyang +4
Improving the training and inference performance of graph neural networks (GNNs) is faced with a challenge uncommon in general neural networks: creating mini-batches requires a lot…
Supervised Linear Dimension-Reduction Methods: Review, Extensions, and Comparisons
Shaojie Xu, Joel Vaughan, Jie Chen +2
Principal component analysis (PCA) is a well-known linear dimension-reduction method that has been widely used in data analysis and modeling. It is an unsupervised learning techniq…
Bias, Fairness, and Accountability with AI and ML Algorithms
Nengfeng Zhou, Zach Zhang, Vijayan N. Nair +3
The advent of AI and ML algorithms has led to opportunities as well as challenges. In this paper, we provide an overview of bias and fairness issues that arise with the use of ML a…
CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks
Ruchir Puri, David S. Kung, Geert Janssen +14
Over the last several decades, software has been woven into the fabric of every aspect of our society. As software development surges and code infrastructure of enterprise applicat…
Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification
Jie Chen, Shouzhen Chen, Mingyuan Bai +3
Graph neural networks (GNN) have been ubiquitous in graph node classification tasks. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' informa…
Noise Injection-based Regularization for Point Cloud Processing
Xiao Zang, Yi Xie, Siyu Liao +2
Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regulariza…
Linear Iterative Feature Embedding: An Ensemble Framework for Interpretable Model
Agus Sudjianto, Jinwen Qiu, Miaoqi Li +1
A new ensemble framework for interpretable model called Linear Iterative Feature Embedding (LIFE) has been developed to achieve high prediction accuracy, easy interpretation and ef…
Directed Acyclic Graph Neural Networks
Veronika Thost, Jie Chen
Graph-structured data ubiquitously appears in science and engineering. Graph neural networks (GNNs) are designed to exploit the relational inductive bias exhibited in graphs; they…
Generating a Doppelganger Graph: Resembling but Distinct
Yuliang Ji, Ru Huang, Jie Chen +1
Deep generative models, since their inception, have become increasingly more capable of generating novel and perceptually realistic signals (e.g., images and sound waves). With the…
Discrete Graph Structure Learning for Forecasting Multiple Time Series
Chao Shang, Jie Chen, Jinbo Bi
Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a mult…
Supervised Machine Learning Techniques: An Overview with Applications to Banking
Linwei Hu, Jie Chen, Joel Vaughan +4
This article provides an overview of Supervised Machine Learning (SML) with a focus on applications to banking. The SML techniques covered include Bagging (Random Forest or RF), Bo…
Surrogate Locally-Interpretable Models with Supervised Machine Learning Algorithms
Linwei Hu, Jie Chen, Vijayan N. Nair +1
Supervised Machine Learning (SML) algorithms, such as Gradient Boosting, Random Forest, and Neural Networks, have become popular in recent years due to their superior predictive pe…
Adaptive Explainable Neural Networks (AxNNs)
Jie Chen, Joel Vaughan, Vijayan N. Nair +1
While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the resul…
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
Xiao Zang, Yi Xie, Jie Chen +1
Deep neural networks, while generalize well, are known to be sensitive to small adversarial perturbations. This phenomenon poses severe security threat and calls for in-depth inves…
Embedding Compression with Isotropic Iterative Quantization
Siyu Liao, Jie Chen, Yanzhi Wang +2
Continuous representation of words is a standard component in deep learning-based NLP models. However, representing a large vocabulary requires significant memory, which can cause…
CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator
Huy Phan, Yi Xie, Siyu Liao +2
Deep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many AI fields. Adversarial attack is a method that causes the intended misclas…
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
Tengfei Ma, Jie Chen
Hierarchical abstractions are a methodology for solving large-scale graph problems in various disciplines. Coarsening is one such approach: it generates a pyramid of graphs whereby…
Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
Mark Weber, Giacomo Domeniconi, Jie Chen +4
Anti-money laundering (AML) regulations play a critical role in safeguarding financial systems, but bear high costs for institutions and drive financial exclusion for those on the…