相关论文: Feature Attribution from First Principles

The limited transparency of the inner decision-making mechanism in deep neural networks (DNN) and other machine learning (ML) models has hindered their application in several domains. In order to tackle this issue, feature attribution…

Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing frameworks, such as InterpretDL and OmniXAI, integrate…

Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main…

Training the deep neural networks that dominate NLP requires large datasets. These are often collected automatically or via crowdsourcing, and may exhibit systematic biases or annotation artifacts. By the latter we mean spurious…

PatternAttribution is a recent method, introduced in the vision domain, that explains classifications of deep neural networks. We demonstrate that it also generates meaningful interpretations in the language domain.

The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by citing [16] showing that it is the \emph{unique} method…

Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random…

The study of neural networks from the perspective of Fourier features has garnered significant attention. While existing analytical research suggests that neural networks tend to learn low-frequency features, a clear attribution method for…

We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \emph{attribution} (word importance), we find that these deep networks often…

Attribution methods explain neural network predictions by identifying influential input features, but their evaluation suffers from threshold selection bias that can reverse method rankings and undermine conclusions. Current protocols…

The ability to transfer skills across tasks has the potential to scale up reinforcement learning (RL) agents to environments currently out of reach. Recently, a framework based on two ideas, successor features (SFs) and generalised policy…

The widespread use of Artificial Intelligence (AI) in consequential domains, such as healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods. However, ensuring fairness is often…

Feature Learning aims to extract relevant information contained in data sets in an automated fashion. It is driving force behind the current deep learning trend, a set of methods that have had widespread empirical success. What is lacking…

As deep vision models' popularity rapidly increases, there is a growing emphasis on explanations for model predictions. The inherently explainable attribution method aims to enhance the understanding of model behavior by identifying the…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Metadata attributes (e.g., user and product IDs from reviews) can be incorporated as additional inputs to neural-based NLP models, by modifying the architecture of the models, in order to improve their performance. Recent models however…

Most accurate predictions are typically obtained by learning machines with complex feature spaces (as e.g. induced by kernels). Unfortunately, such decision rules are hardly accessible to humans and cannot easily be used to gain insights…

We study the attribution problem [28] for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of the input image. We propose a new technique called…

In this paper, a Neural network is derived from first principles, assuming only that each layer begins with a linear dimension-reducing transformation. The approach appeals to the principle of Maximum Entropy (MaxEnt) to find the posterior…

We formalise the widespread idea of interpreting neural network decisions as an explicit optimisation problem in a rate-distortion framework. A set of input features is deemed relevant for a classification decision if the expected…