Related papers: Axiomatic Attribution for Deep Networks
The interpretability of deep neural networks is crucial for understanding model decisions in various applications, including computer vision. AttEXplore++, an advanced framework built upon AttEXplore, enhances attribution by incorporating…
The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none. Most current approaches have focused on learning…
Network embedding aims to learn a latent, low-dimensional vector representations of network nodes, effective in supporting various network analytic tasks. While prior arts on network embedding focus primarily on preserving network topology…
Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we…
Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high…
There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based on learning…
Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…
Deep networks realize complex mappings that are often understood by their locally linear behavior at or around points of interest. For example, we use the derivative of the mapping with respect to its inputs for sensitivity analysis, or to…
In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework…
Recently network embedding has gained increasing attention due to its advantages in facilitating network computation tasks such as link prediction, node classification and node clustering. The objective of network embedding is to represent…
This paper introduces the Actuarial Neural Additive Model, an inherently interpretable deep learning model for general insurance pricing that offers fully transparent and interpretable results while retaining the strong predictive power of…
Streaming classification methods assume the number of input features is fixed and always received. But in many real-world scenarios demand is some input features are reliable while others are unreliable or inconsistent. In this paper, we…
We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…
This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation.…
To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…
In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms. As an expository contribution we demonstrate how to re-formulate a wide variety of challenges from deep neural networks, (stochastic)…
Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity…
A network provides powerful means of representing complex relationships between entities by abstracting entities as vertices, and relationships as edges connecting vertices in a graph. Beyond the presence or absence of relationships, a…
Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…
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…