most citedUnderstanding and Unifying Fourteen Attribution Methods with Taylor Interactions

18 citations · 37 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2023

A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier

Hua Tang, Lu Cheng, Ninghao Liu +1

While the accuracy-fairness trade-off has been frequently observed in the literature of fair machine learning, rigorous theoretical analyses have been scarce. To demystify this lon…

cs.CL20232 cited

Mitigating Shortcuts in Language Models with Soft Label Encoding

Zirui He, Huiqi Deng, Haiyan Zhao +2

Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. In this work, we aim to answer the fo…

cs.CR2023

XGBD: Explanation-Guided Graph Backdoor Detection

Zihan Guan, Mengnan Du, Ninghao Liu

Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset…

cs.CV2023

DISPEL: Domain Generalization via Domain-Specific Liberating

Chia-Yuan Chang, Yu-Neng Chuang, Guanchu Wang +2

Domain generalization aims to learn a generalization model that can perform well on unseen test domains by only training on limited source domains. However, existing domain general…

cs.LG20236 cited

DEGREE: Decomposition Based Explanation For Graph Neural Networks

Qizhang Feng, Ninghao Liu, Fan Yang +3

Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data. However, the black-box nature of GNNs prevents users from understanding and trusti…

cs.LG202318 cited

Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions

Huiqi Deng, Na Zou, Mengnan Du +5

Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the fina…