Related papers: Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification

Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification

URL: http://arxiv.org/abs/2209.14974v1
Date: Mon, 26 Sep 2022 08:55:31 GMT
Title: Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification
Authors: Adrien Bennetot, Gianni Franchi, Javier Del Ser, Raja Chatila, Natalia Diaz-Rodriguez
Abstract summary: Greybox XAI is a framework that composes a DNN and a transparent model thanks to the use of a symbolic Knowledge Base (KB) We address the problem of the lack of universal criteria for XAI by formalizing what an explanation is. We show how this new architecture is accurate and explainable in several datasets.
Score: 6.940242990198
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Although Deep Neural Networks (DNNs) have great generalization and prediction capabilities, their functioning does not allow a detailed explanation of their behavior. Opaque deep learning models are increasingly used to make important predictions in critical environments, and the danger is that they make and use predictions that cannot be justified or legitimized. Several eXplainable Artificial Intelligence (XAI) methods that separate explanations from machine learning models have emerged, but have shortcomings in faithfulness to the model actual functioning and robustness. As a result, there is a widespread agreement on the importance of endowing Deep Learning models with explanatory capabilities so that they can themselves provide an answer to why a particular prediction was made. First, we address the problem of the lack of universal criteria for XAI by formalizing what an explanation is. We also introduced a set of axioms and definitions to clarify XAI from a mathematical perspective. Finally, we present the Greybox XAI, a framework that composes a DNN and a transparent model thanks to the use of a symbolic Knowledge Base (KB). We extract a KB from the dataset and use it to train a transparent model (i.e., a logistic regression). An encoder-decoder architecture is trained on RGB images to produce an output similar to the KB used by the transparent model. Once the two models are trained independently, they are used compositionally to form an explainable predictive model. We show how this new architecture is accurate and explainable in several datasets.

Related papers

CHILLI: A data context-aware perturbation method for XAI [3.587367153279351]
The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. We propose a novel framework, CHILLI, for incorporating data context into XAI by generating contextually aware perturbations. This is shown to improve both the soundness and accuracy of the explanations.
arXiv Detail & Related papers (2024-07-10T10:18:07Z)
Reasoning with trees: interpreting CNNs using hierarchies [3.6763102409647526]
We introduce a framework that uses hierarchical segmentation techniques for faithful and interpretable explanations of Convolutional Neural Networks (CNNs) Our method constructs model-based hierarchical segmentations that maintain the model's reasoning fidelity. Experiments show that our framework, xAiTrees, delivers highly interpretable and faithful model explanations.
arXiv Detail & Related papers (2024-06-19T06:45:19Z)
Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
arXiv Detail & Related papers (2023-06-14T23:24:01Z)
SpecXAI -- Spectral interpretability of Deep Learning Models [11.325580593182414]
XAI attempts to develop techniques that temper the impenetrable nature of the models and promote a level of understanding of their behavior. Here we present our contribution to XAI methods in the form of a framework that we term SpecXAI. We show how this framework can be used to not only understand the network but also manipulate it into a linear interpretable symbolic representation.
arXiv Detail & Related papers (2023-02-20T12:36:54Z)
Optimizing Explanations by Network Canonization and Hyperparameter Search [74.76732413972005]
Rule-based and modified backpropagation XAI approaches often face challenges when being applied to modern model architectures. Model canonization is the process of re-structuring the model to disregard problematic components without changing the underlying function. In this work, we propose canonizations for currently relevant model blocks applicable to popular deep neural network architectures.
arXiv Detail & Related papers (2022-11-30T17:17:55Z)
Towards Prototype-Based Self-Explainable Graph Neural Network [37.90997236795843]
We study a novel problem of learning prototype-based self-explainable GNNs that can simultaneously give accurate predictions and prototype-based explanations on predictions. The learned prototypes are also used to simultaneously make prediction for for a test instance and provide instance-level explanation.
arXiv Detail & Related papers (2022-10-05T00:47:42Z)
A Practical Tutorial on Explainable AI Techniques [5.671062637797752]
This tutorial is meant to be the go-to handbook for any audience with a computer science background. It aims at getting intuitive insights of machine learning models, accompanied with straight, fast, and intuitive explanations out of the box.
arXiv Detail & Related papers (2021-11-13T17:47:31Z)
Dynamic Inference with Neural Interpreters [72.90231306252007]
We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
arXiv Detail & Related papers (2021-10-12T23:22:45Z)
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
arXiv Detail & Related papers (2020-10-01T17:51:19Z)
Explainability in Deep Reinforcement Learning [68.8204255655161]
We review recent works in the direction to attain Explainable Reinforcement Learning (XRL) In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box.
arXiv Detail & Related papers (2020-08-15T10:11:42Z)
Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge [96.92252296244233]
Large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. We show that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements. Our work paves a path towards open-domain systems that constantly improve by interacting with users who can instantly correct a model by adding simple natural language statements.
arXiv Detail & Related papers (2020-06-11T17:02:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.