Integrated Gradients
PulseAugur coverage of Integrated Gradients — every cluster mentioning Integrated Gradients across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
图神经网络解释方法揭示生物网络中的疾病特征
研究人员评估了四种流行的图神经网络（GNN）解释方法，以了解它们在识别生物网络中疾病相关结构方面的有效性。利用合成数据和乳腺癌RNA测序数据，研究发现不同的方法在揭示不同类型的生物信号方面表现出色，例如单节点驱动因素或分布式通路。通过结合多种解释器的共识得分并纳入拓扑信息，研究人员改进了关键癌症基因的优先级排序和生物学相关信号通路的恢复。
-
New methods enhance AI model explainability for images and tabular data
Researchers have developed two new methods for improving feature attribution in machine learning models. Spectral Integrated Gradients (SIG) uses singular value decomposition to create attribution paths that progress fr…
-
AI explainability research proposes new baseline for medical imaging
Researchers have introduced a new concept called "semantic missingness" for explainability methods in medical AI. This approach defines a baseline for path attribution techniques like Integrated Gradients not just as an…
-
New method enhances time series model explainability across multiple domains
Researchers have developed a new method called Cross-domain Integrated Gradients to improve the explainability of time series models. This technique generalizes traditional saliency map methods, allowing for feature att…
-
FRInGe paper introduces Fisher-Rao Integrated Gradients for improved AI model attribution
Researchers have introduced FRInGe, a novel method for improving gradient-based attribution in machine learning models. FRInGe addresses limitations of existing techniques like Integrated Gradients by defining a referen…
-
GRALIS framework unifies linear attribution methods for deep neural networks
Researchers have introduced GRALIS, a novel mathematical framework designed to unify various linear attribution methods used in Explainable AI (XAI). This framework establishes a canonical representation for attribution…
-
Rhamba framework integrates attention and Mamba for fMRI self-supervised learning
Researchers have developed Rhamba, a novel framework for self-supervised learning on resting-state fMRI data. This framework combines region-aware masking with hybrid Attention-Mamba architectures to improve the analysi…
-
New MA-GIG method improves deep neural network feature attribution reliability
Researchers have introduced Manifold-Aligned Guided Integrated Gradients (MA-GIG), a novel technique for improving the reliability of feature attribution in deep neural networks. This method addresses limitations of exi…
-
VAMP-Net uses AI to predict drug resistance in tuberculosis with high accuracy
Researchers have developed VAMP-Net, a novel dual-pathway neural network designed to predict drug resistance in Mycobacterium tuberculosis. The network combines a Set Attention Transformer for analyzing genomic variants…
-
Delta-XAI framework enhances time series model explainability with temporal focus
Researchers have introduced Delta-XAI, a new framework designed to explain changes in predictions made by online time series monitoring models. This framework addresses limitations in existing methods that often analyze…