Related papers: Mechanistic Interpretability as Statistical Estima…
We propose a new method to estimate structural parameters in multi-way networks while controlling for rich structures of fixed effects. The method is based on a series of classification tasks and is agnostic to both the number and structure…
In imaging inverse problems, one seeks to recover an image from missing/corrupted measurements. Because such problems are ill-posed, there is great motivation to quantify the uncertainty induced by the measurement-and-recovery process.…
Artificial intelligence models and methods commonly lack causal interpretability. Despite the advancements in interpretable machine learning (IML) methods, they frequently assign importance to features which lack causal influence on the…
Industrial processes generate complex data that challenge fault detection systems, often yielding opaque or underwhelming results despite advanced machine learning techniques. This study tackles such difficulties using the Tennessee Eastman…
The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications, such as justice system, drug/vaccination design, and medical diagnosis. Although there are effective methods to train…
Causal dependence modelling of multivariate extremes is intended to improve our understanding of the relationships amongst variables associated with rare events. Regular variation provides a standard framework in the study of extremes. This…
Causal inference is central to many areas of artificial intelligence, including complex reasoning, planning, knowledge-base construction, robotics, explanation, and fairness. An active community of researchers develops and enhances…
Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. Several approaches have been recently considered to encode attributes in the latent space to enhance its…
Although the widespread use of AI systems in today's world is growing, many current AI systems are found vulnerable due to hidden bias and missing information, especially in the most commonly used forecasting system. In this work, we…
The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as algorithmic alignment. At the same time, recent advances in…
Fair machine learning seeks to identify and mitigate biases in predictions against unfavorable populations characterized by demographic attributes, such as race and gender. Recently, a few works have extended fairness to graph data, such as…
Machine-learning technologies for learning dynamical systems from data play an important role in engineering design. This research focuses on learning continuous linear models from data. Stability, a key feature of dynamic systems, is…
The challenge of creating interpretable models has been taken up by two main research communities: ML researchers primarily focused on lower-level explainability methods that suit the needs of engineers, and HCI researchers who have more…
Recent work by Anthropic on Mechanistic interpretability claims to understand and control Large Language Models by extracting human-interpretable features from their neural activation patterns using sparse autoencoders (SAEs). If…
Most major retailers today have multiple divisions focused on various aspects, such as marketing, supply chain, online customer experience, store customer experience, employee productivity, and vendor fulfillment. They also regularly…
The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…
Survival analysis is central to clinical research, informing patient prognoses, guiding treatment decisions, and optimising resource allocation. Accurate time-to-event predictions not only improve quality of life but also reveal risk…
Social scientists are increasingly turning to unstructured datasets to unlock new empirical insights, e.g., estimating descriptive statistics of or causal effects on quantitative measures derived from text, audio, or video data. In many…
Network reconstruction is the task of inferring the unseen interactions between elements of a system, based only on their behavior or dynamics. This inverse problem is in general ill-posed, and admits many solutions for the same…
Probabilistic circuits (PCs) are models that allow exact and tractable probabilistic inference. In contrast to neural networks, they are often assumed to be well-calibrated and robust to out-of-distribution (OOD) data. In this paper, we…