activity
20182022
most citedUncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks

5 citations · 7 across the 6 of their papers we have counts for

collaborators

11 papers

cs.LG2022

Faith: An Efficient Framework for Transformer Verification on GPUs

Boyuan Feng, Tianqi Tang, Yuke Wang +5

Transformer verification draws increasing attention in machine learning research and industry. It formally verifies the robustness of transformers against adversarial attacks such…

cs.LG2021

DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions

Yuke Wang, Boyuan Feng, Yufei Ding

As the key advancement of the convolutional neural networks (CNNs), depthwise separable convolutions (DSCs) are becoming one of the most popular techniques to reduce the computatio…

cs.LG20205 cited

Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks

Boyuan Feng, Yuke Wang, Zheng Wang +1

With the increasing popularity of graph-based learning, graph neural networks (GNNs) emerge as the essential tool for gaining insights from graphs. However, unlike the conventional…

cs.LG2020

Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers

Boyuan Feng, Yuke Wang, Xu Li +1

Graph neural networks (GNNs) have achieved high performance in analyzing graph-structured data and have been widely deployed in safety-critical areas, such as finance and autonomou…

cs.LG20202 cited

SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization

Boyuan Feng, Yuke Wang, Xu Li +3

With the increasing popularity of graph-based learning, Graph Neural Networks (GNNs) win lots of attention from the research and industry field because of their high accuracy. Howe…

cs.DC2019

AccD: A Compiler-based Framework for Accelerating Distance-related Algorithms on CPU-FPGA Platforms

Yuke Wang, Boyuan Feng, Gushu Li +3

As a promising solution to boost the performance of distance-related algorithms (e.g., K-means and KNN), FPGA-based acceleration attracts lots of attention, but also comes with num…