activity
20202022
most citedImproving the Adversarial Robustness of NLP Models by Information Bottleneck

21 citations · 55 across the 8 of their papers we have counts for

collaborators

14 papers

cs.LG2022

CARE: Certifiably Robust Learning with Reasoning via Variational Inference

Jiawei Zhang, Linyi Li, Ce Zhang +1

Despite great recent advances achieved by deep neural networks (DNNs), they are often vulnerable to adversarial attacks. Intensive research efforts have been made to improve the ro…

cs.LG2022★ 5 cited

Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM

Chulin Xie, Pin-Yu Chen, Qinbin Li +3

Federated learning (FL) enables distributed resource-constrained devices to jointly train shared models while keeping the training data local for privacy purposes. Vertical FL (VFL…

cs.CL2022★ 21 cited

Improving the Adversarial Robustness of NLP Models by Information Bottleneck

Cenyuan Zhang, Xiang Zhou, Yixin Wan +3

Existing studies have demonstrated that adversarial examples can be directly attributed to the presence of non-robust features, which are highly predictive, but can be easily manip…

cs.LG2022★ 4 cited

Certifying Some Distributional Fairness with Subpopulation Decomposition

Mintong Kang, Linyi Li, Maurice Weber +3

Extensive efforts have been made to understand and improve the fairness of machine learning models based on observational metrics, especially in high-stakes domains such as medical…

cs.LG2022★ 8 cited

Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines

Bojan Karlaš, David Dao, Matteo Interlandi +4

Developing modern machine learning (ML) applications is data-centric, of which one fundamental challenge is to understand the influence of data quality to ML training -- "Which tra…

cs.LG2022★ 4 cited

Certifying Out-of-Domain Generalization for Blackbox Functions

Maurice Weber, Linyi Li, Boxin Wang +3

Certifying the robustness of model performance under bounded data distribution drifts has recently attracted intensive interest under the umbrella of distributional robustness. How…