Negative Flux Aggregation to Estimate Feature Attributions
This addresses the need for better explainability in DNNs for security and transparency, though it appears incremental as it builds on existing attribution methods.
The paper tackles the problem of explaining deep neural network predictions by estimating input feature attributions using a novel Negative Flux Aggregation (NeFLAG) formulation, which outperforms competing methods in generating more faithful attribution maps as demonstrated in experiments.
There are increasing demands for understanding deep neural networks' (DNNs) behavior spurred by growing security and/or transparency concerns. Due to multi-layer nonlinearity of the deep neural network architectures, explaining DNN predictions still remains as an open problem, preventing us from gaining a deeper understanding of the mechanisms. To enhance the explainability of DNNs, we estimate the input feature's attributions to the prediction task using divergence and flux. Inspired by the divergence theorem in vector analysis, we develop a novel Negative Flux Aggregation (NeFLAG) formulation and an efficient approximation algorithm to estimate attribution map. Unlike the previous techniques, ours doesn't rely on fitting a surrogate model nor need any path integration of gradients. Both qualitative and quantitative experiments demonstrate a superior performance of NeFLAG in generating more faithful attribution maps than the competing methods. Our code is available at \url{https://github.com/xinli0928/NeFLAG}