相关论文: Delta-Audit: Explaining What Changes When Models C…

Deep learning-based diagnostic models often suffer performance drops due to distribution shifts between training (source) and test (target) domains. Collecting and labeling sufficient target domain data for model retraining represents an…

Explainable AI (XAI) is increasingly essential as modern models become more complex and high-stakes applications demand transparency, trust, and regulatory compliance. Existing global attribution methods often incur high computational…

Much of the reported progress in file-level software defect prediction (SDP) is, in reality, nothing but an illusion of accuracy. Over the last decades, machine learning and deep learning models have reported increasing performance across…

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…

Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned models. However,…

Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, including dataset curation, model interpretability, data valuation.…

Heterogeneity is an unwanted variation when analyzing aggregated datasets from multiple sources. Though different methods have been proposed for heterogeneity adjustment, no systematic theory exists to justify these methods. In this work,…

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…

Data Science (DS) has become a cornerstone for modern software, enabling data-driven decisions to improve companies services. Following modern software development practices, data scientists use third-party libraries to support their tasks.…

Graph domain adaptation has recently enabled knowledge transfer across different graphs. However, without the semantic information on target graphs, the performance on target graphs is still far from satisfactory. To address the issue, we…

As machine learning models are increasingly used in critical decision-making settings (e.g., healthcare, finance), there has been a growing emphasis on developing methods to explain model predictions. Such \textit{explanations} are used to…

Fully test-time adaptation aims at adapting a pre-trained model to the test stream during real-time inference, which is urgently required when the test distribution differs from the training distribution. Several efforts have been devoted…

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…

Feature attribution is a fundamental task in both machine learning and data analysis, which involves determining the contribution of individual features or variables to a model's output. This process helps identify the most important…

Financial markets are noisy and non-stationary, making alpha mining highly sensitive to backtest noise and regime shifts. While recent agentic frameworks improve automation, they often lack controllable multi-round search and reliable reuse…

When the prediction of a black-box machine learning model deviates from the true observation, what can be said about the reason behind that deviation? This is a fundamental and ubiquitous question that the end user in a business or…

This study proposes DeltaSHAP, a novel explainable artificial intelligence (XAI) algorithm specifically designed for online patient monitoring systems. In clinical environments, discovering the causes driving patient risk evolution is…

The increasing complexity of AI systems has made understanding their behavior critical. Numerous interpretability methods have been developed to attribute model behavior to three key aspects: input features, training data, and internal…

Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to…

Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of…