activity
20152023
most citedZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

1.8k citations · 2.3k across the 59 of their papers we have counts for

collaborators
Showing 2017Show all

8 papers · 1 filter

cs.LG2017

Incremental Eigenpair Computation for Graph Laplacian Matrices: Theory and Applications

Pin-Yu Chen, Baichuan Zhang, Mohammad Al Hasan

The smallest eigenvalues and the associated eigenvectors (i.e., eigenpairs) of a graph Laplacian matrix have been widely used in spectral clustering and community detection. Howeve…

stat.ML20172 cited

Revisiting Spectral Graph Clustering with Generative Community Models

Pin-Yu Chen, Lingfei Wu

The methodology of community detection can be divided into two principles: imposing a network model on a given graph, or optimizing a designed objective function. The former provid…

cs.SI201710 cited

Principled Multilayer Network Embedding

Weiyi Liu, Pin-Yu Chen, Sailung Yeung +2

Multilayer network analysis has become a vital tool for understanding different relationships and their interactions in a complex system, where each layer in a multilayer network d…

stat.ML20178 cited

Multilayer Spectral Graph Clustering via Convex Layer Aggregation: Theory and Algorithms

Pin-Yu Chen, Alfred O. Hero

Multilayer graphs are commonly used for representing different relations between entities and handling heterogeneous data processing tasks. Non-standard multilayer graph clustering…

stat.ML20171.8k cited

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

Pin-Yu Chen, Huan Zhang, Yash Sharma +2

Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not l…

cs.LG20175 cited

Can GAN Learn Topological Features of a Graph?

Weiyi Liu, Pin-Yu Chen, Hal Cooper +3

This paper is first-line research expanding GANs into graph topology analysis. By leveraging the hierarchical connectivity structure of a graph, we have demonstrated that generativ…