Related papers: Explaining Drift using Shapley Values
The notion of concept drift refers to the phenomenon that the data generating distribution changes over time; as a consequence machine learning models may become inaccurate and need adjustment. In this paper we consider the problem of…
Deployed machine learning models are confronted with the problem of changing data over time, a phenomenon also called concept drift. While existing approaches of concept drift detection already show convincing results, they require true…
Existing drift detection methods focus on designing sensitive test statistics. They treat the detection threshold as a fixed hyperparameter, set once to balance false alarms and late detections, and applied uniformly across all datasets and…
Evolving borrower behaviors, shifting economic conditions, and changing regulatory landscapes continuously reshape the data distributions underlying modern credit-scoring systems. Conventional explainability techniques, such as SHAP, assume…
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time. We are interested in an identification of those features, that are most relevant for the observed drift.…
Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of model outputs has…
Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its…
In a world that constantly changes, it is crucial to understand how those changes impact different systems, such as industrial manufacturing or critical infrastructure. Explaining critical changes, referred to as concept drift in the field…
Fine-tuning pretrained language models can improve task performance while subtly altering the evidence a model relies on. We propose a training-time interpretability view that tracks token-level attributions across finetuning epochs. We…
We introduce a new approach for decoupling trends (drift) and changepoints (shifts) in time series. Our locally adaptive model-based approach for robustly decoupling combines Bayesian trend filtering and machine learning based…
Developing modern machine learning (ML) applications is data-centric, of which one fundamental challenge is to understand the influence of data quality to ML training -- "Which training examples are 'guilty' in making the trained ML model…
In data streams, the data distribution of arriving observations at different time points may change - a phenomenon called concept drift. While detecting concept drift is a relatively mature area of study, solutions to the uncertainty…
Detecting drift in performance of Machine Learning (ML) models is an acknowledged challenge. For ML models to become an integral part of business applications it is essential to detect when an ML model drifts away from acceptable operation.…
Concept drift refers to the change of data distributions over time. While drift poses a challenge for learning models, requiring their continual adaption, it is also relevant in system monitoring to detect malfunctions, system failures, and…
Systems and individuals produce data continuously. On the Internet, people share their knowledge, sentiments, and opinions, provide reviews about services and products, and so on. Automatically learning from these textual data can provide…
The Shapley value provides a principled framework for fairly distributing rewards among participants according to their individual contributions. While prior work has applied this concept to data valuation in machine learning, existing…
The performance of machine learning models relies heavily on the quality of input data, yet real-world applications often face significant data-related challenges. A common issue arises when curating training data or deploying models: two…
Continuous machine learning pipelines are common in industrial settings where models are periodically trained on data streams. Unfortunately, concept drifts may occur in data streams where the joint distribution of the data X and label y,…
Unpacking and comprehending how black-box machine learning algorithms make decisions has been a persistent challenge for researchers and end-users. Explaining time-series predictive models is useful for clinical applications with high…
Data Shapley has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning. It can effectively identify helpful or harmful data points for a learning algorithm. In this paper, we…