Unlearning-based Neural Interpretations
Gradient-based interpretations often require an anchor point of comparison to avoid
saturation in computing feature importance. We show that current baselines defined using …
saturation in computing feature importance. We show that current baselines defined using …
Enhancing Pre-trained Deep Learning Model with Self-Adaptive Reflection
In the text mining area, prevalent deep learning models primarily focus on mapping input
features to result of predicted outputs, which exhibit a deficiency in self-dialectical thinking …
features to result of predicted outputs, which exhibit a deficiency in self-dialectical thinking …
Data-Faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables
Q Sun, H Xia, J Liu - The Thirty-eighth Annual Conference on …, 2024 - openreview.net
The state-of-the-art feature attribution methods often neglect the influence of unobservable
confounders, posing a risk of misinterpretation, especially when it is crucial for the …
confounders, posing a risk of misinterpretation, especially when it is crucial for the …
Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attribution Methods
Attribution methods compute importance scores for input features to explain the output
predictions of deep models. However, accurate assessment of attribution methods is …
predictions of deep models. However, accurate assessment of attribution methods is …
QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations
Deep Neural Networks (DNNs) stand out as one of the most prominent approaches within
the Machine Learning (ML) domain. The efficacy of DNNs has surged alongside recent …
the Machine Learning (ML) domain. The efficacy of DNNs has surged alongside recent …
Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
The explainability of deep neural networks (DNNs) is critical for trust and reliability in AI
systems. Path-based attribution methods, such as integrated gradients (IG), aim to explain …
systems. Path-based attribution methods, such as integrated gradients (IG), aim to explain …