Optimizing costly black-box functions within a constrained evaluation budget presents significant challenges in many real-world applications. Surrogate Optimization (SO) is a common resolution, yet its proprietary nature introduced by the complexity of surrogate models and the sampling core (e.g., acquisition functions) often leads to a lack of explainability and transparency. While existing literature has primarily concentrated on enhancing convergence to global optima, the practical interpretation of newly proposed strategies remains underexplored, especially in batch evaluation settings. In this paper, we propose \emph{Inclusive} Explainability Metrics for Surrogate Optimization (IEMSO), a comprehensive set of model-agnostic metrics designed to enhance the transparency, trustworthiness, and explainability of the SO approaches. Through these metrics, we provide both intermediate and post-hoc explanations to practitioners before and after performing expensive evaluations to gain trust. We consider four primary categories of metrics, each targeting a specific aspect of the SO process: Sampling Core Metrics, Batch Properties Metrics, Optimization Process Metrics, and Feature Importance. Our experimental evaluations demonstrate the significant potential of the proposed metrics across different benchmarks.
Machine learning is revolutionizing nutrition science by enabling systems to learn from data and make intelligent decisions. However, the complexity of these models often leads to challenges in understanding their decision-making processes, necessitating the development of explainability techniques to foster trust and increase model transparency. An under-explored type of explanation is cohort explanation, which provides explanations to groups of instances with similar characteristics. Unlike traditional methods that focus on individual explanations or global model behavior, cohort explainability bridges the gap by providing unique insights at an intermediate granularity. We propose a novel framework for identifying cohorts within a dataset based on local feature importance scores, aiming to generate concise descriptions of the clusters via tags. We evaluate our framework on a food-based inflammation prediction model and demonstrated that the framework can generate reliable explanations that match domain knowledge.
In recent years, censored quantile regression has enjoyed an increasing popularity for survival analysis while many existing works rely on linearity assumptions. In this work, we propose a Global Censored Quantile Random Forest (GCQRF) for predicting a conditional quantile process on data subject to right censoring, a forest-based flexible, competitive method able to capture complex nonlinear relationships. Taking into account the randomness in trees and connecting the proposed method to a randomized incomplete infinite degree U-process (IDUP), we quantify the prediction process' variation without assuming an infinite forest and establish its weak convergence. Moreover, feature importance ranking measures based on out-of-sample predictive accuracy are proposed. We demonstrate the superior predictive accuracy of the proposed method over a number of existing alternatives and illustrate the use of the proposed importance ranking measures on both simulated and real data.
Interpretability is a topic that has been in the spotlight for the past few years. Most existing interpretability techniques produce interpretations in the form of rules or feature importance. These interpretations, while informative, may be harder to understand for non-expert users and therefore, cannot always be considered as adequate explanations. To that end, explanations in natural language are often preferred, as they are easier to comprehend and also more presentable to end-users. This work introduces an early concept for a novel pipeline that can be used in text classification tasks, offering predictions and explanations in natural language. It comprises of two models: a classifier for labelling the text and an explanation generator which provides the explanation. The proposed pipeline can be adopted by any text classification task, given that ground truth rationales are available to train the explanation generator. Our experiments are centred around the tasks of sentiment analysis and offensive language identification in Greek tweets, using a Greek Large Language Model (LLM) to obtain the necessary explanations that can act as rationales. The experimental evaluation was performed through a user study based on three different metrics and achieved promising results for both datasets.
Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is necessary to ensure fairness, safety, and legal compliance. In this paper we consider one class of such tasks, tabular dataset classification, and propose a novel neuro-symbolic architecture, Neural Reasoning Networks (NRN), that is scalable and generates logically sound textual explanations for its predictions. NRNs are connected layers of logical neurons which implement a form of real valued logic. A training algorithm (R-NRN) learns the weights of the network as usual using gradient descent optimization with backprop, but also learns the network structure itself using a bandit-based optimization. Both are implemented in an extension to PyTorch (https://github.com/IBM/torchlogic) that takes full advantage of GPU scaling and batched training. Evaluation on a diverse set of 22 open-source datasets for tabular classification demonstrates performance (measured by ROC AUC) which improves over multi-layer perceptron (MLP) and is statistically similar to other state-of-the-art approaches such as Random Forest, XGBoost and Gradient Boosted Trees, while offering 43% faster training and a more than 2 orders of magnitude reduction in the number of parameters required, on average. Furthermore, R-NRN explanations are shorter than the compared approaches while producing more accurate feature importance scores.
Gradient-based interpretations often require an anchor point of comparison to avoid saturation in computing feature importance. We show that current baselines defined using static functions--constant mapping, averaging or blurring--inject harmful colour, texture or frequency assumptions that deviate from model behaviour. This leads to accumulation of irregular gradients, resulting in attribution maps that are biased, fragile and manipulable. Departing from the static approach, we propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent. Our method discovers reliable baselines and succeeds in erasing salient features, which in turn locally smooths the high-curvature decision boundaries. Our analyses point to unlearning as a promising avenue for generating faithful, efficient and robust interpretations.
Wireless communication has evolved significantly, with 6G offering groundbreaking capabilities, particularly for IoT. However, the integration of IoT into 6G presents new security challenges, expanding the attack surface due to vulnerabilities introduced by advanced technologies such as open RAN, terahertz (THz) communication, IRS, massive MIMO, and AI. Emerging threats like AI exploitation, virtualization risks, and evolving attacks, including data manipulation and signal interference, further complicate security efforts. As 6G standards are set to be finalized by 2030, work continues to align security measures with technological advances. However, substantial gaps remain in frameworks designed to secure integrated IoT and 6G systems. Our research addresses these challenges by utilizing tree-based machine learning algorithms to manage complex datasets and evaluate feature importance. We apply data balancing techniques to ensure fair attack representation and use SHAP and LIME to improve model transparency. By aligning feature importance with XAI methods and cross-validating for consistency, we boost model accuracy and enhance IoT security within the 6G ecosystem.
Objective: To improve prediction of Chronic Kidney Disease (CKD) progression to End Stage Renal Disease (ESRD) using machine learning (ML) and deep learning (DL) models applied to an integrated clinical and claims dataset of varying observation windows, supported by explainable AI (XAI) to enhance interpretability and reduce bias. Materials and Methods: We utilized data about 10,326 CKD patients, combining their clinical and claims information from 2009 to 2018. Following data preprocessing, cohort identification, and feature engineering, we evaluated multiple statistical, ML and DL models using data extracted from five distinct observation windows. Feature importance and Shapley value analysis were employed to understand key predictors. Models were tested for robustness, clinical relevance, misclassification errors and bias issues. Results: Integrated data models outperformed those using single data sources, with the Long Short-Term Memory (LSTM) model achieving the highest AUC (0.93) and F1 score (0.65). A 24-month observation window was identified as optimal for balancing early detection and prediction accuracy. The 2021 eGFR equation improved prediction accuracy and reduced racial bias, notably for African American patients. Discussion: Improved ESRD prediction accuracy, results interpretability and bias mitigation strategies presented in this study have the potential to significantly enhance CKD and ESRD management, support targeted early interventions and reduce healthcare disparities. Conclusion: This study presents a robust framework for predicting ESRD outcomes in CKD patients, improving clinical decision-making and patient care through multi-sourced, integrated data and AI/ML methods. Future research will expand data integration and explore the application of this framework to other chronic diseases.
Synthesizing relational data has started to receive more attention from researchers, practitioners, and industry. The task is more difficult than synthesizing a single table due to the added complexity of relationships between tables. For the same reason, benchmarking methods for synthesizing relational data introduces new challenges. Our work is motivated by a lack of an empirical evaluation of state-of-the-art methods and by gaps in the understanding of how such an evaluation should be done. We review related work on relational data synthesis, common benchmarking datasets, and approaches to measuring the fidelity and utility of synthetic data. We combine the best practices and a novel robust detection approach into a benchmarking tool and use it to compare six methods, including two commercial tools. While some methods are better than others, no method is able to synthesize a dataset that is indistinguishable from original data. For utility, we typically observe moderate correlation between real and synthetic data for both model predictive performance and feature importance.
Feature selection is a critical task in machine learning and statistics. However, existing feature selection methods either (i) rely on parametric methods such as linear or generalized linear models, (ii) lack theoretical false discovery control, or (iii) identify few true positives. Here, we introduce a general feature selection method with finite-sample false discovery control based on applying integrated path stability selection (IPSS) to arbitrary feature importance scores. The method is nonparametric whenever the importance scores are nonparametric, and it estimates q-values, which are better suited to high-dimensional data than p-values. We focus on two special cases using importance scores from gradient boosting (IPSSGB) and random forests (IPSSRF). Extensive nonlinear simulations with RNA sequencing data show that both methods accurately control the false discovery rate and detect more true positives than existing methods. Both methods are also efficient, running in under 20 seconds when there are 500 samples and 5000 features. We apply IPSSGB and IPSSRF to detect microRNAs and genes related to cancer, finding that they yield better predictions with fewer features than existing approaches.
Breast cancer's complexity and variability pose significant challenges in understanding its progression and guiding effective treatment. This study aims to integrate protein sequence data with expression levels to improve the molecular characterization of breast cancer subtypes and predict clinical outcomes. Using ProtGPT2, a language model designed for protein sequences, we generated embeddings that capture the functional and structural properties of proteins sequence. These embeddings were integrated with protein expression level to form enriched biological representations, which were analyzed using machine learning methods like ensemble K-means for clustering and XGBoost for classification. Our approach enabled successful clustering of patients into biologically distinct groups and accurately predicted clinical outcomes such as survival and biomarkers status, achieving high performance metrics, notably an F1 score of 0.88 for survival and 0.87 for biomarkers status prediction. Feature importance analysis identified KMT2C, CLASP2, and MYO1B as key proteins involved in hormone signaling, cytoskeletal remodeling, and therapy resistance in hormone receptor-positive and triple-negative breast cancer, with potential influence on breast cancer subtype behavior and progression. Furthermore, protein-protein interaction networks and correlation analyses revealed functional interdependencies among proteins that may influence breast cancer subtype behavior and progression. These findings suggest that integrating protein sequence and expression data provides valuable insights into tumor biology and has significant potential to enhance personalized treatment strategies in breast cancer care.
Important variables of processes are often categorical, i.e. names or labels representing, e.g. categories of inputs, or types of reactors or a sequence of steps. In this work, we use Natural Language Processing Models to derive embeddings of such inputs that represent their actual meaning, or reflect the "distances" between categories, i.e. how similar or dissimilar they are. This is a marked difference from the current standard practice of using binary, or one-hot encoding to replace categorical variables with sequences of ones and zeros. Combined with dimensionality reduction techniques, either linear such as Principal Component Analysis, or nonlinear such as Uniform Manifold Approximation and Projection, the proposed approach leads to a meaningful, low-dimensional feature space. The significance of obtaining meaningful embeddings is illustrated in the context of an industrial coating process for cutting tools that includes both numerical and categorical inputs. In this industrial process, subject matter expertise suggests that the categorical inputs are critical for determining the final outcome but this cannot be taken into account with the current state-of-the-art. The proposed approach enables feature importance which is a marked improvement compared to the current state-of-the-art in the encoding of categorical variables. The proposed approach is not limited to the case-study presented here and is suitable for applications with similar mix of categorical and numerical critical inputs.
As complex machine learning models continue to find applications in high-stakes decision-making scenarios, it is crucial that we can explain and understand their predictions. Post-hoc explanation methods provide useful insights by identifying important features in an input $\mathbf{x}$ with respect to the model output $f(\mathbf{x})$. In this work, we formalize and study two precise notions of feature importance for general machine learning models: sufficiency and necessity. We demonstrate how these two types of explanations, albeit intuitive and simple, can fall short in providing a complete picture of which features a model finds important. To this end, we propose a unified notion of importance that circumvents these limitations by exploring a continuum along a necessity-sufficiency axis. Our unified notion, we show, has strong ties to other popular definitions of feature importance, like those based on conditional independence and game-theoretic quantities like Shapley values. Crucially, we demonstrate how a unified perspective allows us to detect important features that could be missed by either of the previous approaches alone.
Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to high overhead of parameter and bitrate usage, or face challenges in multi-objective optimization under a unified representation, failing to achieve both performance and efficiency. To this end, we propose Multi-Path Aggregation (MPA) integrated into existing coding models for joint human-machine vision, unifying the feature representation with an all-in-one architecture. MPA employs a predictor to allocate latent features among task-specific paths based on feature importance varied across tasks, maximizing the utility of shared features while preserving task-specific features for subsequent refinement. Leveraging feature correlations, we develop a two-stage optimization strategy to alleviate multi-task performance degradation. Upon the reuse of shared features, as low as 1.89% parameters are further augmented and fine-tuned for a specific task, which completely avoids extensive optimization of the entire model. Experimental results show that MPA achieves performance comparable to state-of-the-art methods in both task-specific and multi-objective optimization across human viewing and machine analysis tasks. Moreover, our all-in-one design supports seamless transitions between human- and machine-oriented reconstruction, enabling task-controllable interpretation without altering the unified model. Code is available at https://github.com/NJUVISION/MPA.
Disturbances to the climate system, both natural and anthropogenic, have far reaching impacts that are not always easy to identify or quantify using traditional climate science analyses or causal modeling techniques. In this paper, we develop a novel technique for discovering and ranking the chain of spatio-temporal downstream impacts of a climate source, referred to herein as a source-impact pathway, using Random Forest Regression (RFR) and SHapley Additive exPlanation (SHAP) feature importances. Rather than utilizing RFR for classification or regression tasks (the most common use case for RFR), we propose a fundamentally new workflow in which we: (i) train random forest (RF) regressors on a set of spatio-temporal features of interest, (ii) calculate their pair-wise feature importances using the SHAP weights associated with those features, and (iii) translate these feature importances into a weighted pathway network (i.e., a weighted directed graph), which can be used to trace out and rank interdependencies between climate features and/or modalities. Importantly, while herein we employ RFR and SHAP feature importance in steps (i) and (ii) of our algorithm, our novel workflow is in no way tied to these approaches, which could be replaced with any regression method and sensitivity method. We adopt a tiered verification approach to verify our new pathway identification methodology. In this approach, we apply our method to ensembles of data generated by running two increasingly complex benchmarks: (i) a set of synthetic coupled equations, and (ii) a fully coupled simulation of the 1991 eruption of Mount Pinatubo in the Philippines performed using a modified version 2 of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SMv2). We find that our RFR feature importance-based approach can accurately detect known pathways of impact for both test cases.
In tabular biomedical data analysis, tuning models to high accuracy is considered a prerequisite for discussing feature importance, as medical practitioners expect the validity of feature importance to correlate with performance. In this work, we challenge the prevailing belief, showing that low-performing models may also be used for feature importance. We propose experiments to observe changes in feature rank as performance degrades sequentially. Using three synthetic datasets and six real biomedical datasets, we compare the rank of features from full datasets to those with reduced sample sizes (data cutting) or fewer features (feature cutting). In synthetic datasets, feature cutting does not change feature rank, while data cutting shows higher discrepancies with lower performance. In real datasets, feature cutting shows similar or smaller changes than data cutting, though some datasets exhibit the opposite. When feature interactions are controlled by removing correlations, feature cutting consistently shows better stability. By analyzing the distribution of feature importance values and theoretically examining the probability that the model cannot distinguish feature importance between features, we reveal that models can still distinguish feature importance despite performance degradation through feature cutting, but not through data cutting. We conclude that the validity of feature importance can be maintained even at low performance levels if the data size is adequate, which is a significant factor contributing to suboptimal performance in tabular medical data analysis. This paper demonstrates the potential for utilizing feature importance analysis alongside statistical analysis to compare features relatively, even when classifier performance is not satisfactory.
Best performing approaches for scholarly document quality prediction are based on embedding models, which do not allow direct explanation of classifiers as distinct words no longer correspond to the input features for model training. Although model-agnostic explanation methods such as Local interpretable model-agnostic explanations (LIME) can be applied, these produce results with questionable correspondence to the ML model. We introduce a new feature importance method, Self-model Rated Entities (SMER), for logistic regression-based classification models trained on word embeddings. We show that SMER has theoretically perfect fidelity with the explained model, as its prediction corresponds exactly to the average of predictions for individual words in the text. SMER allows us to reliably determine which words or entities positively contribute to predicting impactful articles. Quantitative and qualitative evaluation is performed through five diverse experiments conducted on 50.000 research papers from the CORD-19 corpus. Through an AOPC curve analysis, we experimentally demonstrate that SMER produces better explanations than LIME for logistic regression.
Diabetes is a chronic disease characterised by a high risk of developing diabetic nephropathy, which, in turn, is the leading cause of end-stage chronic kidney disease. The early identification of individuals at heightened risk of such complications or their exacerbation can be of paramount importance to set a correct course of treatment. In the present work, from the data collected in the DARWIN-Renal (DApagliflozin Real-World evIdeNce-Renal) study, a nationwide multicentre retrospective real-world study, we develop an array of logistic regression models to predict, over different prediction horizons, the crossing of clinically relevant glomerular filtration rate (eGFR) thresholds for patients with diabetes by means of variables associated with demographic, anthropometric, laboratory, pathology, and therapeutic data. In doing so, we investigate the impact of information coming from patient's past visits on the model's predictive performance, coupled with an analysis of feature importance through the Boruta algorithm. Our models yield very good performance (AUROC as high as 0.98). We also show that the introduction of information from patient's past visits leads to improved model performance of up to 4%. The usefulness of past information is further corroborated by a feature importance analysis.
Large language models (LLMs) have shown remarkable capabilities in various natural language tasks and are increasingly being applied in healthcare domains. This work demonstrates a new LLM-powered disease risk assessment approach via streaming human-AI conversation, eliminating the need for programming required by traditional machine learning approaches. In a COVID-19 severity risk assessment case study, we fine-tune pre-trained generative LLMs (e.g., Llama2-7b and Flan-t5-xl) using a few shots of natural language examples, comparing their performance with traditional classifiers (i.e., Logistic Regression, XGBoost, Random Forest) that are trained de novo using tabular data across various experimental settings. We develop a mobile application that uses these fine-tuned LLMs as its generative AI (GenAI) core to facilitate real-time interaction between clinicians and patients, providing no-code risk assessment through conversational interfaces. This integration not only allows for the use of streaming Questions and Answers (QA) as inputs but also offers personalized feature importance analysis derived from the LLM's attention layers, enhancing the interpretability of risk assessments. By achieving high Area Under the Curve (AUC) scores with a limited number of fine-tuning samples, our results demonstrate the potential of generative LLMs to outperform discriminative classification methods in low-data regimes, highlighting their real-world adaptability and effectiveness. This work aims to fill the existing gap in leveraging generative LLMs for interactive no-code risk assessment and to encourage further research in this emerging field.
This study evaluates the ability of large language models (LLMs) to map biomedical ontology terms to their corresponding ontology IDs across the Human Phenotype Ontology (HPO), Gene Ontology (GO), and UniProtKB terminologies. Using counts of ontology IDs in the PubMed Central (PMC) dataset as a surrogate for their prevalence in the biomedical literature, we examined the relationship between ontology ID prevalence and mapping accuracy. Results indicate that ontology ID prevalence strongly predicts accurate mapping of HPO terms to HPO IDs, GO terms to GO IDs, and protein names to UniProtKB accession numbers. Higher prevalence of ontology IDs in the biomedical literature correlated with higher mapping accuracy. Predictive models based on receiver operating characteristic (ROC) curves confirmed this relationship. In contrast, this pattern did not apply to mapping protein names to Human Genome Organisation's (HUGO) gene symbols. GPT-4 achieved a high baseline performance (95%) in mapping protein names to HUGO gene symbols, with mapping accuracy unaffected by prevalence. We propose that the high prevalence of HUGO gene symbols in the literature has caused these symbols to become lexicalized, enabling GPT-4 to map protein names to HUGO gene symbols with high accuracy. These findings highlight the limitations of LLMs in mapping ontology terms to low-prevalence ontology IDs and underscore the importance of incorporating ontology ID prevalence into the training and evaluation of LLMs for biomedical applications.