相关论文: Interpretability-Guided Bi-objective Optimization:…

Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are otherwise opaque to a user. There are a plethora of existing…

Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions,…

Learning directed acyclic graphs (DAGs) from data is a challenging task both in theory and in practice, because the number of possible DAGs scales superexponentially with the number of nodes. In this paper, we study the problem of learning…

Information-Geometric Optimization (IGO) is a unified framework of stochastic algorithms for optimization problems. Given a family of probability distributions, IGO turns the original optimization problem into a new maximization problem on…

Despite all the benefits of automated hyperparameter optimization (HPO), most modern HPO algorithms are black-boxes themselves. This makes it difficult to understand the decision process which leads to the selected configuration, reduces…

Integrated Gradients (IG) and PatternAttribution (PA) are two established explainability methods for neural networks. Both methods are theoretically well-founded. However, they were designed to overcome different challenges. In this work,…

A wide variety of model explanation approaches have been proposed in recent years, all guided by very different rationales and heuristics. In this paper, we take a new route and cast interpretability as a statistical inference problem. We…

Deep learning has become the standard approach for most machine learning tasks. While its impact is undeniable, interpreting the predictions of deep learning models from a human perspective remains a challenge. In contrast to model…

In language model interpretability research, \textbf{circuit tracing} aims to identify which internal features causally contributed to a particular output and how they affected each other, with the goal of explaining the computations…

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

Black-Box Optimization (BBO) methods can find optimal policies for systems that interact with complex environments with no analytical representation. As such, they are of interest in many Artificial Intelligence (AI) domains. Yet classical…

Knowledge graphs (KGs) are becoming essential resources for many downstream applications. However, their incompleteness may limit their potential. Thus, continuous curation is needed to mitigate this problem. One of the strategies to…

Black-box algorithms are designed to optimize functions without relying on their underlying analytical structure or gradient information, making them essential when gradients are inaccessible or difficult to compute. Traditional methods for…

We propose a novel score-based approach to learning a directed acyclic graph (DAG) from observational data. We adapt a recently proposed continuous constrained optimization formulation to allow for nonlinear relationships between variables…

Interpretability techniques aim to provide the rationale behind a model's decision, typically by explaining either an individual prediction (local explanation, e.g. 'why is this patient diagnosed with this condition') or a class of…

In recent years, there has been growing attention to interpretable machine learning models which can give explanatory insights on their behaviour. Thanks to their interpretability, decision trees have been intensively studied for…

Score-based models have recently been introduced as a richer framework to model distributions in high dimensions and are generally more suitable for generative tasks. In score-based models, a generative task is formulated using a parametric…

We propose the Preference Guided Iterated Pareto Referent Optimisation (PG-IPRO) for urban route planning for people with different accessibility requirements and preferences. With this algorithm the user can interact with the system by…

Directed acyclic graphs (DAGs) are commonly used to represent causal relationships among random variables in graphical models. Applications of these models arise in the study of physical, as well as biological systems, where directed edges…

Attribution algorithms are frequently employed to explain the decisions of neural network models. Integrated Gradients (IG) is an influential attribution method due to its strong axiomatic foundation. The algorithm is based on integrating…