Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 74 for “"Spurious Correlations"”.
-
Informed regularization Aiding the identification of spurious correlations
… intends to model with a data set and what correlations a model makes from the true content of the data. By presenting three novel methods that can aid a developer with the task of identify ing spurious correlations, it was possible to present information regarding a spurious correlation …
-
Towards externally valid machine learning: A spurious correlations perspective
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01
-
Spurious Correlations from Supervised Models to Agentic Systems: Detection, Benchmarking, and Mitigation
… the training data but incidental to the task, a spurious correlation that holds until it breaks. This dissertation argues that such failures, though they take a different form in each training paradigm, can be examined through a single counterfactual lens: keep the task-inherent features fixed, …
-
Learning More and Knowing Less: Big Data, Spurious Correlations, and the Problem of Ignorance
… that help us sort through the datasets bring up spurious correlations. This project explores the implications of spurious correlations on our epistemic endeavours through the lens of ignorance. I will draw on recent scholarship in agnotology, the study of ignorance, namely by Nancy Tuana, Robert …
-
Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
Spurious correlations are a major source of errors for machine learning models, in particular when aiming for group-level fairness. It has been recently shown that a powerful approach to combat spurious correlations is to re-train the last layer on a balanced validation dataset, isolating robust …
-
Using Generative Models for Data Augmentation in Medical Imaging
… for a population subgroup hence leading to spurious correlation in data. For the first case, we propose a novel object-centric data augmentation model that can learn the shape variations for the objects of interest and augment the object in place without modifying the rest of the image. For …
-
Explainable AI for malware opcode sequence analysis and explainability-motivated saliency-map based spurious correlation robustness in images
… Risk Minimisation and learns to rely on spurious correlations present in the data. Meanwhile, the teacher is trained to actively avoid these spurious correlations by minimising alignment with the student’s saliency maps. This encourages the teacher to focus on more semantically meaningful …
-
TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE
Machine learning (ML) models often rely on spurious correlations in the training data, leading to performance degradation and unreliability when processing inputs under distribution shifts. This thesis systematically studies the robustness to distribution shifts for ML models from a data-centric …
-
Generalization in Dynamic Environments: Foundations and Algorithms
… of dynamic environments. First, we investigate spurious correlations: patterns which are predictive of the target class in the training dataset but irrelevant to the true classification function. We present an empirical analysis of popular algorithms for the mitigation of spurious correlations …
-
Group Robustness under the Microscope: How Class Imbalance Shapes the Effectiveness of Last-Layer Retraining
… empirical risk minimization (ERM) often rely on spurious correlations, leading to severe performance degradation on underrepresented subpopulations. This thesis provides a comprehensive examination of group robustness in fine-tuned neural networks, focusing on how class imbalance and data …
-
Causal Machine Learning in the Era of Large Language Models: Approaches, Perspectives, and Applications
… explainability, especially in the presence of spurious correlations and distribution shifts. These issues often stem from the reliance on statistical associations rather than underlying causal mechanisms. Causality offers a principled framework to address these limitations by enabling models to …
-
Detecting diabetic foot osteomyelitis in plain radiographic images using Deep Learning
… affect performance in this context are called spurious features, which are features unrelated to the target class that co-occur with the target class in the training dataset. The application of data balancing via filtering to mitigate spurious correlations is a common approach. However, this …
-
Aerosol-cloud-precipitation interactions
… conditions has the ability to generate spurious correlations between cloud and aerosol properties.</p> <p>This work presents a new way to investigate aerosol-cloud-precipitation interactions while accounting for the influence of meteorology on cloud and aerosol. The clouds are separated …
-
ENHANCING PRIVACY IN MACHINE LEARNING THROUGH THE MINIMIZATION OF MEMORIZATION
… It also strengthens the model against memorizing spurious correlations, enhancing the model's generalizability.
-
AdFair-CLIP: Adversarial Fair Contrastive Language-Image Pre-Training for Chest X-Rays
… sensitive attributes, thereby mitigating spurious correlations and improving prediction fairness. We conduct comprehensive experiments on chest X-ray (CXR) datasets, and show that AdFair-CLIP significantly enhances both fairness and diagnostic accuracy, while maintaining robust …
-
Compositions, logratios and geostatistics: An application to iron ore
… has occurred and this can be shown to produce spurious correlations. Compositional geostatistics is an approach developed to ensure that the constant sum constraint is respected in estimation while removing dependencies on the spurious correlations. This study tests the applicability of this …
-
Causal Machine Learning: Exploiting Changes for Generalization and Beyond
… models often fail in such settings, relying on spurious correlations rather than true causal structures. Causal representation learning, which combines ML with causal inference, offers a solution by capturing underlying causal mechanisms, enhancing model adaptability and robustness across …
-
TOWARDS TRUSTWORTHY LANGUAGE MODELS
… poor out-of-distribution generalization due to spurious correlations and fragile prompt optimization. During inference, LLMs tend to produce overconfident predictions, making unreliable outputs difficult to identify. During alignment, optimizing multiple human preference objectives, such as …
-
An application of Box–Jenkins transfer function analysis to consumption–income relationship in South Africa
… patterns shared by Y and X that can produce spurious correlations. The primary aim of this study was therefore to use the Box-Jenkins Transfer Function analysis to fit a model that related petroleum consumption to disposable income> The final Transfer Function Model z1t=)C(1-w1 B)/((1-δ1 B) …
-
Exploiting Correspondences in Multi-perspective Data Learning
… performance and the learning of potential spurious correlations. To overcome these issues, we design a cross-attention mechanism combined with global-local constraints to learn inter-view correspondence in a weakly supervised manner implicitly. Spurious correlations have also been observed …
Page 1 of 4