Negative Flux Aggregation to Estimate Feature Attributions

Authors: Xin Li, Deng Pan, Chengyin Li, Yao Qiang, Dongxiao Zhu

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Both qualitative and quantitative experiments demonstrate a superior performance of Ne FLAG in generating more faithful attribution maps than the competing methods.
Researcher Affiliation Academia Xin Li , Deng Pan , Chengyin Li , Yao Qiang and Dongxiao Zhu Department of Computer Science, Wayne State University, USA {xinlee, pan.deng, cli, yao, dzhu}@wayne.edu
Pseudocode Yes Algorithm 1 Ne FLAG(f, x, n, Sx, ϵ, m)
Open Source Code Yes Our code is available at https://github.com/xinli0928/Ne FLAG.
Open Datasets Yes Dataset. The Image Net [Deng et al., 2009] dataset is used for all of our experiments.
Dataset Splits Yes We randomly select 5,000 samples from Image Net validation dataset with 5 samples from each class as a good representation of the classes.
Hardware Specification No The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper mentions using 'captum' but does not provide any specific version numbers for software dependencies or libraries.
Experiment Setup Yes The Ne FLAG is configured as follows: ϵ-sphere radius is set to ϵ = 0.1, and the number of random negative flux point x is n = 20. (...) For AGI, we adopt the default parameter settings reported in [Pan et al., 2021], i.e., step size ϵ = 0.05, number of false classes n = 20.