CA-LIG is a unified hierarchical attribution method that computes layer-wise Integrated Gradients fused with class-specific attention gradients to generate signed, context-sensitive explanations for transformer models.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A framework combining stochastic zeroth-order optimization and dynamic low-rank surrogate modeling with an implicit projector-splitting integrator enables end-to-end training of hybrid neural networks containing black-box physical layers and reaches near-digital accuracy on vision, audio, and text任务
DP-CDA generates synthetic data via class-specific randomized mixing to claim stronger privacy guarantees and higher predictive utility than prior data-publishing methods under equivalent privacy budgets.
citing papers explorer
-
Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models
CA-LIG is a unified hierarchical attribution method that computes layer-wise Integrated Gradients fused with class-specific attention gradients to generate signed, context-sensitive explanations for transformer models.
-
Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
A framework combining stochastic zeroth-order optimization and dynamic low-rank surrogate modeling with an implicit projector-splitting integrator enables end-to-end training of hybrid neural networks containing black-box physical layers and reaches near-digital accuracy on vision, audio, and text任务
-
DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing
DP-CDA generates synthetic data via class-specific randomized mixing to claim stronger privacy guarantees and higher predictive utility than prior data-publishing methods under equivalent privacy budgets.