Proposes using Wasserstein barycenters for model ensembling in multiclass/multilabel learning.
problem Finding consensus between models in multiclass/multilabel learning settings.
method Uses Wasserstein (W.) barycenters to find consensus between models, incorporating semantic side information.
result Wasserstein ensembling balances confidence and semantics in model agreement.
Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight relevant words for a predicted class label, experiments based on word deleti…
Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning. We propose a novel zero-shot l…
Obtaining compact and discriminative features is one of the major challenges in many of the real-world image classification tasks such as face verification and object recognition. One possible approach is to represent input image on the basis of high-level features that carry semantic meaning which humans can understan…
We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions. Two desirable characteristics of an attribution-based explanation are: (1) $\texti…
RELAX provides first attribution-based explanations for representations.
problem Lack of methods to explain what influences learned representations.
method RELAX, a first approach for attribution-based explanations of representations, measuring similarities in representation space.
result Significantly outperforms gradient-based baseline and models uncertainty in explanations.
APD method decomposes neural network parameters into simple, faithful components.
problem Understanding the internal mechanisms learned by neural networks.
method Attribution-based Parameter Decomposition (APD) method.
result Demonstrated effectiveness in recovering features, separating computations, and identifying representations.
The paper detects and identifies bias in data using a counterfactual approach.
problem Detecting and identifying bias in data, especially in medical image classification.
method A global explanation framework using the counterfactual approach to identify bias causing artifacts.
result Black frames significantly influence Convolutional Neural Network's prediction, changing benign to malignant.
A Triangle Generative Adversarial Network (Δ-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples. Δ-GAN consists of four neural networks, two ge…
Computer-aided diagnosis systems for classification of different type of skin lesions have been an active field of research in recent decades. It has been shown that introducing lesions and their attributes masks into lesion classification pipeline can greatly improve the performance. In this paper, we propose a framew…
Paper proposes TPathMine model for more accurate user attribute prediction.
problem Predicting user attributes from click data in heterogeneous networks.
method HetPathMine model with meta-path weights optimized for user emotional preferences.
result TPathMine model achieves higher accuracy in user attribute prediction.
Paper tackles product categorization with structured and unstructured attributes for large-scale eCommerce.
problem Challenges in categorizing products with thousands of classes and millions of products.
method Compares hierarchical and flat models, uses Deep Learning for feature extraction, combines structured and unstructured attributes.
result Flat models perform better in specific cases, and the proposed approach handles faulty attribute names and values.
Maximum drawdown, the largest cumulative loss from peak to trough, is one of the most widely used indicators of risk in the fund management industry, but one of the least developed in the context of measures of risk. We formalize drawdown risk as Conditional Expected Drawdown (CED), which is the tail mean of maximum dr…
A new method for disentangled latent spaces in VAEs that can manipulate attributes.
problem Disentangled representation of attributes in latent spaces of VAEs.
method Attribute-based regularization loss to enforce monotonic relationships between attributes and latent codes.
result Manipulation of attributes in latent spaces post-training.
Paper proposes a method to adapt domains without target data using attribute information.
problem Domain adaptation without target data when prior attribute changes exist.
method Reweight source data with estimated sample-wise weights based on attribute prior.
result Method provides more precise transferability estimation than attribute-based reweighting.
Optimal transport framework for zero-shot learning.
problem Generalized zero-shot learning of unseen classes.
method Conditional generative model and optimal transport between generated and real features.
result Optimal transport-based method outperforms state-of-the-art methods.
The paper formalizes feature attribution to address inconsistent definitions and evaluate methods.
problem Inconsistent definitions of feature relevance in feature attribution.
method Formalization based on relaxed functional dependence, extended to instance-wise setting.
result State-of-the-art methods often fail to verify necessary properties for candidate selection.
MKD learns MTS attributes to reconstruct and cluster unseen classes.
problem Reconstructing and clustering unseen multivariate time-series.
method Multiple-kernel dictionary learning (MKD) to learn semantic attributes.
result MKD provides interpretable reconstruction and high clustering performance.
In this article we discuss some of the consequences of the mixed membership perspective on time series analysis. In its most abstract form, a mixed membership model aims to associate an individual entity with some set of attributes based on a collection of observed data. Although much of the literature on mixed members…
A method for authorship attribution based on function word adjacency networks (WANs) is introduced. Function words are parts of speech that express grammatical relationships between other words but do not carry lexical meaning on their own. In the WANs in this paper, nodes are function words and directed edges stand in…
Improved scalability and interpretability in training data attribution.
problem Identifying which training data drives specific behaviors, especially unintended ones.
method Leveraging interpretable structures within the model to attribute model behavior to semantic directions, not individual test examples.
result Simple probe-based attribution methods are first-order approximations of Concept Influence that achieve comparable performance while being over an order-of-magnitude faster.
Study evaluates deep learning models for solar flare prediction with interpretability analysis.
problem Lack of interpretability in deep learning models for solar flare prediction.
method Proximity-based metric for analyzing attribution maps generated by Guided Grad-CAM.
result Models' predictions align with active region characteristics, offering insights into their behavior.
ExCIR provides efficient, consistent, and scalable explainability for complex models.
problem Complex models lack transparency and require efficient, stable, and scalable explainability methods.
method ExCIR uses correlation-aware feature attribution with robust centering and groupwise aggregation.
result ExCIR delivers trustworthy agreement with global baselines and full model rankings, reduces runtime, and scales to large datasets.
CDLEEDS detects local changes in evolving data streams for accurate feature attributions.
problem Local feature attributions become obsolete in evolving data streams.
method CDLEEDS, a flexible framework for detecting local change and concept drift.
result CDLEEDS reliably detects both local and global concept drift.
SHAP Distance assesses semantic fidelity of synthetic tabular data.
problem Semantic fidelity of synthetic tabular data is not well evaluated.
method SHAP Distance, defined as cosine distance between global SHAP attribution vectors.
result SHAP Distance detects semantic discrepancies overlooked by standard measures.
Enhances community detection in correlated networks with node attributes.
problem Community detection in multiple networks with correlated node attributes and edges.
method Introduced the correlated Contextual Stochastic Block Model (CSBM), developed a two-step matching procedure.
result Algorithm recovers exact node correspondence, enabling enhanced community detection.
By building on a recently introduced genetic-inspired attribute-based conceptual framework for safety risk analysis, we propose a novel methodology to compute construction univariate and bivariate construction safety risk at a situational level. Our fully data-driven approach provides construction practitioners and aca…
Survey reviews explainability in AI for healthcare, emphasizing trust and transparency.
problem Lack of transparency hinders AI adoption in healthcare.
method Comprehensive literature review to guide explainable AI design.
result Quantitative evaluation metrics are needed for some explainability properties.
New findings show local attributions can't be both robust and provide recourse.
problem Ensuring machine learning systems are accountable and provide actionable recourse options.
method Formal definition of recourse sensitivity and counterexamples for popular attribution methods.
result It is impossible for any single attribution method to be both robust and provide recourse.
Paper presents a new framework for sequence classification.
problem Sequence classification in real-world applications.
method Reference-based sequence classification framework.
result New sequence classification algorithms achieve comparable accuracy.
Dual-stage sEMG classification improves gesture recognition accuracy.
problem Improving accuracy in hand gesture recognition from sEMG signals.
method Dual-stage classification approach: first stage groups similar activities, second stage classifies within groups.
result Dual-stage classification yields significantly higher accuracy than single-stage approach.
A novel method for classification with rejection using ensemble of cost-sensitive classifiers.
problem Avoid risky misclassification in error-critical applications.
method Learning an ensemble of cost-sensitive classifiers.
result Improved classification accuracy and flexibility in loss selection.
The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification…
Few-shot image classification is improved by correcting CNNs' texture bias.
problem Few-shot image classification performance is hindered by CNNs' texture bias.
method Corrected CNNs' texture bias using a simpler method than state-of-the-art approaches.
result State-of-the-art performance on miniImageNet task achieved.
Paper introduces LPCs for robust classification with performance bounds.
problem Conventional classification techniques constrain rules and use surrogate losses.
method Robust risk minimization (RRM) for unconstrained classification rules, optimizing 0-1 loss.
result LPCs provide performance bounds and competitive performance with state-of-the-art techniques.
New NHCAs improve multi-category classification efficiency.
problem Efficient multi-category classification for real-world problems.
method Twin SVM (TWSVM), Generalized eigenvalue proximal SVM (GEPSVM), Regularized GEPSVM (RegGEPSVM), and Improved GEPSVM (IGEPSVM) with OAA, BT, and TDS approaches.
result TDS-TWSVM outperforms other methods in classification accuracy.
Paper compares XGB and BPNN for music style classification.
problem Efficient music style classification using different methods.
method Feature extraction for timbral texture, rhythmic content, and pitch content; comparative evaluation of XGB and BPNN.
result XGB outperforms BPNN for small datasets in music classification.
Deep reinforcement learning improves classification accuracy for imbalanced datasets.
problem Imbalanced datasets challenge conventional classification algorithms.
method Formulated as a sequential decision-making process, solved using deep Q-learning network.
result Proposed model outperforms other imbalanced classification algorithms.
Classification outperforms regression in portfolio construction, yielding higher Sharpe ratios.
problem Determining which machine learning approach (classification vs. regression) is more effective for portfolio construction.
method Used stacking ensemble of gradient boosted tree, random forest, and neural network models.
result Classification yields higher Sharpe ratios and economically significant alphas compared to regression.
C-HMCNN(h) improves HMC classification by leveraging class hierarchy.
problem Hierarchical multi-label classification with class hierarchy constraints.
method Exploits class hierarchy to produce coherent predictions for multi-label classification.
result C-HMCNN(h) outperforms state-of-the-art models in HMC classification.
Advances few-shot classification by treating it as supervised learning and proposing new training techniques.
problem Formulating the ability of humans to learn from limited data in machine learning.
method Formulated few-shot classification as a supervised learning problem and introduced multi-episode and cross-way training techniques.
result Proposed training strategies accelerate the training process without accuracy loss.
Improves NILM with multi-label SRC, outperforming state-of-the-art.
problem Non-intrusive load monitoring (NILM) for energy disaggregation.
method Modified multi-label sparse representation based classification (SRC).
result Significant improvement over state-of-the-art techniques with minimal training data.
New approach improves classification guarantees by focusing on direction rather than regression risk.
problem Improving classification guarantees in binary classification problems.
method Establishing a geometric distinction between classification and regression, leveraging scale invariance.
result Improved guarantees for classification risk compared to regression risk.
Study selective classification with halfspaces, achieving error bounds under Gaussian distributions.
problem Modeling relationships in subsets of data defined by selection rules.
method Sparse linear classifiers for subsets defined by halfspaces, focusing on Gaussian feature distributions.
result First PAC-learning algorithm for homogeneous halfspace selectors with error guarantee $\bigO*{\sqrt{\mathrm{opt}}}$.
New method for robust trajectory classification without parameters.
problem Trajectory classification accuracy and robustness.
method Parameter-free approach to find best trajectory partition and dimension combination.
result Promising preliminary results show improved robustness.
We study realizations of Lie algebras by vector fields. A correspondence between classification of transitive local realizations and classification of subalgebras is generalized to the case of regular local realizations. A reasonable classification problem for general realizations is rigorously formulated and an algori…
A new network-based high-level data classification method using betweenness centrality.
problem Traditional data classification techniques focus on physical features, while high-level classification considers semantic meaning.
method Proposes a network-based high-level classification technique using betweenness centrality.
result Competent classification performance in nine real datasets compared to traditional models.
This thesis evaluates text-based vs audio-based classification of mental health interviews.
problem Classifying psychiatric illness using text-based methods.
method Design and evaluate a text classification network on mental health interviews, using belabBERT.
result Text-based classification is a strong alternative to audio-based methods.