DeepAI AI Chat
Log In Sign Up

Explaining Visual Models by Causal Attribution

by   Álvaro Parafita, et al.
Universitat de Barcelona

Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent the data distribution subject to interventions. With these models, we can compute counterfactuals, new samples that will inform us how the model reacts to feature changes on our input. We propose a novel explanation methodology based on Causal Counterfactuals and identify the limitations of current Image Generative Models in their application to counterfactual creation.


Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End

To explain a machine learning model, there are two main approaches: feat...

Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement

Causal models are playing an increasingly important role in machine lear...

Explanatory causal effects for model agnostic explanations

This paper studies the problem of estimating the contributions of featur...

Principled Knowledge Extrapolation with GANs

Human can extrapolate well, generalize daily knowledge into unseen scena...

Aligning Faithful Interpretations with their Social Attribution

We find that the requirement of model interpretations to be faithful is ...

Counterfactual Generation with Knockoffs

Human interpretability of deep neural networks' decisions is crucial, es...

CausalX: Causal Explanations and Block Multilinear Factor Analysis

By adhering to the dictum, "No causation without manipulation (treatment...