KernelSHAP
PulseAugur coverage of KernelSHAP — every cluster mentioning KernelSHAP across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New NObSP framework enhances neural network interpretability
Researchers have introduced NObSP (Nonlinear Oblique Subspace Projections), a novel framework designed to enhance the interpretability of deep neural networks. This method decomposes network predictions into explicit pe…
-
New GroupSegment SHAP method enhances time-series model interpretability
Researchers have developed GroupSegment SHAP (GS-SHAP), a new method for explaining multivariate time-series models. Unlike previous approaches that treat feature and time axes independently, GS-SHAP constructs explanat…
-
New method explains AI optimization recommendations using GradientSHAP and LLMs
Researchers have developed a novel method to explain process control optimization recommendations using a combination of GradientSHAP and implicit differentiation. This approach integrates Implicit Function Theorem (IFT…
-
New theory defines limits for AI explanation methods
Researchers have developed a new theoretical framework to understand the limitations of masking-based AI explanation methods like KernelSHAP and LIME. By modeling the explanation process as communication over a query ch…
-
Researchers develop Shapley value explainers for temporal graph neural networks
Researchers have developed two new model-agnostic explainers for Temporal Graph Neural Networks (TGNNs), utilizing Shapley and Owen values. These methods aim to make the predictions of TGNNs, which combine spatial and t…