Search Results for author:
Found 8 papers, 6 papers with code
Do Concept Bottleneck Models Obey Locality?
Deep learning models trained under this paradigm heavily rely on the assumption that neural networks can learn to predict the presence or absence of a given concept independently of other concepts.
Estimation of Concept Explanations Should be Uncertainty Aware
We believe the improved quality of uncertainty-aware concept explanations make them a strong candidate for more reliable model interpretation.
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT).
Leveraging Task Structures for Improved Identifiability in Neural Network Representations
This work extends the theory of identifiability in supervised learning by considering the consequences of having access to a distribution of tasks.
Use Perturbations when Learning from Explanations
Machine learning from explanations (MLX) is an approach to learning that uses human-provided explanations of relevant or irrelevant features for each input to ensure that model predictions are right for the right reasons.
Robust Explanation Constraints for Neural Networks
Post-hoc explanation methods are used with the intent of providing insights about neural networks and are sometimes said to help engender trust in their outputs.
Towards More Robust Interpretation via Local Gradient Alignment
However, the lack of considering the normalization of the attributions, which is essential in their visualizations, has been an obstacle to understanding and improving the robustness of feature attribution methods.
Fooling Neural Network Interpretations via Adversarial Model Manipulation
We ask whether the neural network interpretation methods can be fooled via adversarial model manipulation, which is defined as a model fine-tuning step that aims to radically alter the explanations without hurting the accuracy of the original models, e. g., VGG19, ResNet50, and DenseNet121.
