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 37 for “"Feature attribution"”.

  1. Proxy Gradient Estimation for Black-Box Feature Attribution

    Feature attribution is a widely adopted form of explanation that reveals the decision-making process of data-driven models. Its objective is to quantify the contribution of input components to a certain model outcome, highlighting the most prominent features and thereby providing an intuitive …

    fu-berlin Repository record for Proxy Gradient Estimation for Black-Box Feature Attribution (opens in a new tab)

  2. The Weighted Möbius Score: A Unified Framework for Feature Attribution

    Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between multiple features. However, the lack of a unified framework has led to a …

    washington Repository record for The Weighted Möbius Score: A Unified Framework for Feature Attribution (opens in a new tab)

  3. Martingale Methods for Structural Change Detection and Feature Attribution in Dynamic Networks

    … without distributional assumptions, exact feature attribution, and early detection with rigorous false alarm control. We construct additive martingale statistics from multiple graph features using conformal prediction, providing false alarm guarantees via Ville's inequality. Our key …

    rowan Repository record for Martingale Methods for Structural Change Detection and Feature Attribution in Dynamic Networks (opens in a new tab)

  4. Understanding Biomedical Machine Learning Models

    … by these algorithms has grown correspondingly. Feature attribution methods are one popular approach to explain these black box models, but are limited in their expressive capacity. We therefore propose three approaches to go beyond the shortcomings of existing feature attribution methods. The …

    washington Repository record for Understanding Biomedical Machine Learning Models (opens in a new tab)

  5. Model Interpretability for Natural Language Processing Applications

    … literature for extracting explana- tions (e.g. feature attribution methods), some faced criticism about how faith- ful they are. Furthermore, explanation faithfulness also depends on the model employed, where highly parametrised models have been shown to produce less faithful explanations. …

    whiterose Download PDF for Model Interpretability for Natural Language Processing Applications (opens in a new tab)

  6. Enhancing deep learning security through explainability and robustness

    … neural networks in production using feature attribution methods, and introduces a new framework for evaluating the robustness of attribution methods. Firstly, TrojDRL is introduced as a tool for exploring and evaluating backdoor attacks on deep reinforcement learning agents. TrojDRL …

    bu Repository record for Enhancing deep learning security through explainability and robustness (opens in a new tab)

  7. Explainable Machine Learning and Applications in Protein-Ligand Complex Structure Prediction

    … and structures. The first portion deals with feature attribution techniques, which attribute attribution scores on a per-instance basis to a machine learning model that represent that model locally around that instance as linear. Three methods are proposed: expected gradients, attribution …

    washington Repository record for Explainable Machine Learning and Applications in Protein-Ligand Complex Structure Prediction (opens in a new tab)

  8. Application of Explainable Graph Neural Networks in Drug and Biomarker Discovery for Human Diseases

    … improves predictive performance and stabilizes feature attribution, enabling more reliable identification of key molecular moieties in lead optimization. Second, this dissertation presents Graph Artificial Intelligence for Pediatric Oncology (GAIPO), a scalable data and model framework that …

    iupui Repository record for Application of Explainable Graph Neural Networks in Drug and Biomarker Discovery for Human Diseases (opens in a new tab) Embargoed until 2027-09-01

  9. G2G - From Data Generation to Model Generalisation

    … to reveal interpretable patterns and improve feature attribution; generating synthetic examples to support few shot classification; extracting structure from unlabelled inputs through self supervised objectives; and creating artificial patterns to guide visual reidentification of animals in …

    auckland-ms Repository record for G2G - From Data Generation to Model Generalisation (opens in a new tab)

  10. Exploring protein-protein interactions using high-throughput datasets and deep learning

    … (3) training models on limited structural features for PPI prediction for specific families, and (3) applying feature attribution techniques to interpret sequence-to-function models. Together, this work supports the continued development of experimental and computational tools to deepen our …

    washington Repository record for Exploring protein-protein interactions using high-throughput datasets and deep learning (opens in a new tab)

  11. Model monitoring in the absence of labeled data via feature attributions distributions

    … that unifies all its sections. It explores feature attribution distributions for both monitoring dimensions. Using these feature attribution explanations, we can exploit their theoretical properties to derive and establish certain guarantees and insights into model monitoring.<br/><br/>For …

    soton Download PDF for Model monitoring in the absence of labeled data via feature attributions distributions (opens in a new tab)

  12. Towards Trustworthy Speech Technologies: Enhancing Explainability and Mitigating Gender Bias in Speech Transcription and Translation

    … in ASR and AST systems. It introduces the first feature attribution technique for modern autoregressive S2T models, providing fine-grained explanations for ASR and AST outputs by assessing the relevance of audio features and previously generated tokens. To investigate factors contributing to …

    trento Repository record for Towards Trustworthy Speech Technologies: Enhancing Explainability and Mitigating Gender Bias in Speech Transcription and Translation (opens in a new tab)

  13. Computational and Data-Driven Design of Perturbed Metal Sites for Catalytic Transformations

    … theories with graph neural network and attribution analysis enables accurate prediction equipped with mechanistic insights. In addition, novel physics effect controlling surface reactivity beyond conventional understanding is uncovered. Secondly, we develop a computational and …

    vt Repository record for Computational and Data-Driven Design of Perturbed Metal Sites for Catalytic Transformations (opens in a new tab)

  14. Scientific machine learning for astrophysical and cosmological inference.

    … are systematically compared using feature-attribution analyses. Second, image-based glitch classification is investigated using convolutional neural networks and Vision Transformers applied to time–frequency spectrograms, with emphasis on robustness under controlled distribution …

    baylor Repository record for Scientific machine learning for astrophysical and cosmological inference. (opens in a new tab)

  15. Towards Reliable and Trustworthy Deep Learning through Explainability and Interpretability

    … new post-hoc explanation methods that improve feature attribution and concept-based explanations. These methods provide faithful decision cues by modeling meaningful feature interactions and extracting faithful coherent concepts, enabling more reliable understanding of why a model predicts a …

    rit Repository record for Towards Reliable and Trustworthy Deep Learning through Explainability and Interpretability (opens in a new tab)

  16. Decoding Lassi Fermentation Using Experimental and Machine Learning Approaches: Longitudinal Analysis of Microbial Kinetics and Physicochemical Dynamics

    … demonstrated strong generalization, and feature attribution analyses identified storage time as the dominant global predictor, with formulation acting as an offset modulator of trajectory magnitude. These results demonstrate that lassi fermentation exhibits nonlinear, …

    tamu Repository record for Decoding Lassi Fermentation Using Experimental and Machine Learning Approaches: Longitudinal Analysis of Microbial Kinetics and Physicochemical Dynamics (opens in a new tab) Embargoed until 2028-05-01

  17. Trustworthy Machine Learning: Specification, Verification, and Explanation

    … certified guarantees on the robustness of feature attribution methods. Building on this, our approach extends to the Stability Certification Algorithm (SCA), offering more flexible and practical guarantees. Together, these methods provide non-trivial, practical, and model-agnostic …

    penn Repository record for Trustworthy Machine Learning: Specification, Verification, and Explanation (opens in a new tab)

  18. Concept drift–resilient malware analysis in evolving threat environments

    … through Integrated Gradients--based feature attribution. Behavioural analysis is performed using capabilities identified by the CAPA tool and techniques from the MITRE ATT&CK framework. The results show that detected drift is often associated with identifiable feature changes and, in …

    qu-belfast Repository record for Concept drift–resilient malware analysis in evolving threat environments (opens in a new tab) Download PDF for Concept drift–resilient malware analysis in evolving threat environments (opens in a new tab)

  19. Extracting and Harnessing Interpretation in Data Mining

    … goal of interpretation is providing the attribution of input features to model outputs. To adapt feature attribution to explaining outlier detection, I propose Contextual Outlier Interpretation (COIN). Second, to overcome the limitation of attribution methods that do not explain internal …

    tamu Repository record for Extracting and Harnessing Interpretation in Data Mining (opens in a new tab)

  20. Towards Explainable Time Series: An Exploration Of Post-hoc Local Explanations From A Multi-disciplinary Perspective

    … We adapt both LIME and SHAP to provide two novel attribution methods which are specifically designed for univariate and multivariate time series. <br/><br/>The Shapley value is one of the most popular methods for value attribution. However, when applied for feature attribution it has been known to …

    bristol Repository record for Towards Explainable Time Series: An Exploration Of Post-hoc Local Explanations From A Multi-disciplinary Perspective (opens in a new tab) Download PDF for Towards Explainable Time Series: An Exploration Of Post-hoc Local Explanations From A Multi-disciplinary Perspective (opens in a new tab)

Page 1 of 2