This paper provides new insight into maximizing F1 scores in the context of binary classification and also in the context of multilabel classification. The harmonic mean of precision and recall, F1 score is widely used to measure the success of a binary classifier when one class is rare. Micro average, macro average, a…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “F1-Score”
Communities in social networks or graphs are sets of well-connected, overlapping vertices. The effectiveness of a community detection algorithm is determined by accuracy in finding the ground-truth communities and ability to scale with the size of the data. In this work, we provide three contributions. First, we show t…
Superior Scoring Rules for Probabilistic Evaluation of Single-Label Multi-Class Classification Taskscs.LG
New scoring rules improve probabilistic classification model evaluation.
problem Traditional scoring rules misalign with the preference for correct classifications.
method Introduces Penalized Brier Score (PBS) and Penalized Logarithmic Loss (PLL) to modify proper scoring rules.
result PBS and PLL better identify optimal checkpoints and early stopping points, leading to superior F1 scores.
In predictive maintenance, model performance is usually assessed by means of precision, recall, and F1-score. However, employing the model with best performance, e.g. highest F1-score, does not necessarily result in minimum maintenance cost, but can instead lead to additional expenses. Thus, we propose to perform model…
Enhances multi-tag classification using low-dimensional vector representations and virtual data.
problem Improving the performance of multi-tag classifiers.
method Embedding raw data into a low-dimensional feature space, then generating virtual data from linear operations on these vectors, to train multi-tag classifiers.
result Significant improvement in F1 scores (up to 224%) compared to training directly with raw data.
LoRAS improves model performance on imbalanced datasets by better oversampling the minority class.
problem Imbalanced datasets lead to poor model performance, especially for the majority class.
method Localized Random Affine Shadowsampling (LoRAS) to oversample minority class data.
result LoRAS generates better ML models in terms of F1-Score and Balanced accuracy compared to SMOTE and its extensions.
Proposes BA method for unbiased time series anomaly detection evaluation.
problem Anomalies in time series data are rare, making F1-score unreliable.
method Introduces Balanced Point Adjustment (BA) to address F1-score bias.
result BA provides fairer evaluation of time series anomaly detectors.
Paper classifies Brazilian music genres using song lyrics with BLSTM network.
problem Classifying Brazilian music genres from lyrics.
method Used BLSTM network combined with SVM, Random Forest, and word embeddings.
result BLSTM outperforms other models with an F1-score of 0.48.
GWN improves multimodal data fusion accuracy for chronic pain patients.
problem Dynamic and unspecified uncertainties in multimodal data fusion.
method Inspired by Global Workspace Theory, GWN is a neural network architecture that dynamically attends to multiple modalities.
result GWN achieved higher F1 scores (0.92 and 0.75) for multimodal discrimination and classification tasks.
To address Task 5 in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 challenge, in this paper, we propose an ensemble learning system. The proposed system consists of three different models, based on convolutional neural network and long short memory recurrent neural network. With extracted …
For technology (like serious games) that aims to deliver interactive learning, it is important to address relevant mental experiences such as reflective thinking during problem solving. To facilitate research in this direction, we present the weDraw-1 Movement Dataset of body movement sensor data and reflective thinkin…
Proposes sigmoidF1 loss for multilabel classification, improving performance metrics.
problem Lack of smooth, tractable loss functions for multilabel classification.
method Introduces sigmoidF1, a smooth F1 score surrogate loss function.
result sigmoidF1 outperforms other loss functions on various datasets and metrics.
This study improves early prediction of CPAP therapy compliance.
problem Predicting early compliance with CPAP therapy to improve patient outcomes.
method Built classifiers for compliance at three CPAP therapy follow-up points.
result Month 3 classifier achieved highest f1-score of 87% in cross-validation and test.
SECRET combines ML and NLP for better real-world task classification.
problem Limited integration of semantic relationships in supervised ML.
method SECRET fuses semantic information from NLP with feature space of supervised ML.
result Up to 14.0% accuracy and 13.1% F1 score improvements over traditional supervised learning.
New model improves DDI extraction with 78.5% macro F1-score.
problem Extracting Drug-Drug Interactions from text.
method Attention-Wrapped Hierarchical BLSTMs.
result Model outperforms state-of-the-art with macro F1-score of 0.785.
Deep learning detects snow avalanches in SAR images with high accuracy.
problem Accurate detection of snow avalanches in remote areas using satellite imagery.
method Fully Convolutional Neural Network trained on manually labeled Sentinel-1 radar images.
result Deep learning model achieves F1 score above 66% compared to 38% for state-of-the-art methods.
Transformer models improve malware classification, especially for imbalanced datasets.
problem Imbalanced multiclass malware classification.
method Bagging-based random transformer forest (RTF) ensemble of pre-trained transformer models (BERT or CANINE).
result Ensemble of pre-trained transformer models achieves state-of-the-art F1-score of 0.6149 on a benchmark dataset.
Improved offensive language detection in tweets with multiple deep learning models.
problem Detecting offensive language in tweets using machine learning.
method Combination of multiple deep learning architectures for classification.
result Achieved macro-average F1-scores of 0.76, 0.68, 0.54 for different tasks.
BERTino is a lightweight Italian DistilBERT model for NLP tasks.
problem High computational and memory demands of large language models.
method Developed a DistilBERT model tailored for Italian language.
result F1 scores comparable to BERTBASE with significant speed improvements.
We study the performance of data-driven, a priori and random approaches to label space partitioning for multi-label classification with a Gaussian Naive Bayes classifier. Experiments were performed on 12 benchmark data sets and evaluated on 5 established measures of classification quality: micro and macro averaged F1 s…
Improved race prediction model outperforms existing methods.
problem Improving race prediction using voter registration data.
method Trained BiLSTM model on voter registration data and created an ensemble.
result Achieved up to 36.8% higher OOS F1 scores than previous models.
Project improves gender-balanced pronoun resolution with BERT.
problem Challenging task in natural language understanding, especially for gendered pronouns.
method BERT-based approach to gender-balanced pronoun resolution.
result Achieved 92% F1 score with lower gender bias.
A new method quantizes LSTM gate parameters without performance loss.
problem Quantization loss in LSTM gate parameters without performance degradation.
method Lossy quantization of gate parameters during training, weight parameters adjust to offset quantization loss.
result F1 score decreased by only 0.7% on Named Entity Recognition dataset.
OT domain adaptation improves aphasia detection across languages.
problem Detecting aphasia in low-resource languages with limited data.
method Utilized OT domain adaptation to map linguistic features across multiple languages.
result OT domain adaptation significantly improved F1 scores for French and Mandarin aphasia detection.
Two randomized algorithms improve hypergraph learning accuracy and efficiency.
problem Efficiently learning and tagging images in hypergraphs.
method Block randomized SVD and conjugate gradient method.
result Both methods achieve high accuracy and reduce computational requirements.
A new method fuses labels from multiple, differently-annotated schemas.
problem Learning from labels that use different schemas.
method Inter-Schema AdapteR (ISAR) to translate labels.
result Significant gains in log-likelihood and F1-score.
Quantum Support Vector Classifier outperforms other QML models in finance fraud detection.
problem Detecting financial fraud using Quantum Machine Learning.
method Comparative study of four QML models: Quantum Support Vector Classifier, Variational Quantum Classifier, Estimator QNN, and Sampler QNN.
result Quantum Support Vector Classifier achieved the highest F1 scores (0.98) for fraud and non-fraud classes.
Improved multiclass classification with class-weighted nearest neighbors.
problem Multiclass classification with large or imbalanced classes.
method Class-weighted k-nearest neighbors algorithm, derived bounds on accuracy and risk.
result Optimized classification metrics like F1 score or Matthew's Correlation Coefficient.
Power Transformer Fault Diagnosis with Intrinsic Time-scale Decomposition and XGBoost Classifiercs.LG
A method uses ITD and XGBoost for precise power transformer fault diagnosis.
problem Fault diagnosis of power transformers using DGA data.
method Ranking DGA parameters by skewness, extracting ITD features, and using an XGBoost classifier.
result The method achieves over 95% accuracy in classification.
Optimal model improves AUC, recall, and F1 score for class-imbalanced business risk.
problem Improving prediction of class-imbalanced business risk.
method Resampling, regularization, and model ensembling techniques.
result Boosting on DT with SMOTE oversampling achieves AUC, recall, and F1 score of 0.8633, 0.9260, and 0.8907, respectively.
Gestalt combines two models to improve SQuAD2.0 performance.
problem Improving the accuracy of answering questions in context paragraphs.
method A stacking ensemble of ALBERT and RoBERTa models, combined with a CNN-based meta-model.
result Best ensemble achieved 87.117 EM and 90.306 F1 scores, improving baseline by 0.55% and 0.61% respectively.
A machine learning model improves MV CDSS accuracy.
problem Limited input data for MV CDSS due to missing physiologic monitoring device information.
method Developed a machine learning classifier for 5 MV modes with high accuracy.
result Average F1-score of 97.52% for per-breath classification.
Improved performance in shape identification tasks using elastic metrics in t-SNE and UMAP.
problem Improper metrics in dimensionality reduction techniques lead to poor performance in machine learning applications.
method Incorporating elastic metrics into t-SNE and UMAP for functional data.
result Improved F1 scores on shape identification tasks for three benchmark datasets.
Proposes a new undersampling method for imbalanced data classification.
problem Challenges of oversampling and undersampling in imbalanced data.
method Bilevel optimization framework for identifying optimal subset of majority training data.
result Improves F1 scores by up to 10% compared to state-of-the-art methods.
Balancing the Scales: A Comprehensive Study on Tackling Class Imbalance in Binary Classificationcs.LG
Study evaluates three class imbalance techniques across diverse datasets.
problem Class imbalance in binary classification tasks.
method Synthetic Minority Over-sampling Technique (SMOTE), Class Weights tuning, Decision Threshold Calibration.
result Decision Threshold Calibration is the most consistently effective technique.
Efficient and precise classification of histological cell nuclei is of utmost importance due to its potential applications in the field of medical image analysis. It would facilitate the medical practitioners to better understand and explore various factors for cancer treatment. The classification of histological cell …
Occupant behavior (OB) and in particular window openings need to be considered in building performance simulation (BPS), in order to realistically model the indoor climate and energy consumption for heating ventilation and air conditioning (HVAC). However, the proposed OB window opening models are often biased towards …
ETHGamDet detects crypto gambling contracts and addresses.
problem Identifying crypto gambling contracts and addresses.
method Multi-modal retrieval methods, LightGBM model with memory components.
result ETHGamDet achieves high F1-scores in address and contract classification.
In this paper, we present our approach for the 2018 Medico Task classifying diseases in the gastrointestinal tract. We have proposed a system based on global features and deep neural networks. The best approach combines two neural networks, and the reproducible experimental results signify the efficiency of the propose…
Novel algorithm optimizes decision trees for nonlinear metrics.
problem Optimizing decision trees for nonlinear metrics like F1-score.
method Bi-objective optimisation approach to find optimal trees on Pareto frontier.
result The optimal tree for nonlinear metrics lies on the Pareto frontier.
T2IVAE detects anomalies in time series data with high accuracy.
problem Detecting anomalies in noisy, complex time series data.
method Unsupervised model based on NVAE and GANs, transforming 1D to 2D images.
result T2IVAE outperforms other models on various datasets.
This paper explores using KDE for balanced sampling in imbalanced datasets.
problem Imbalanced class distribution in data science.
method Kernel density estimation (KDE) for resampling the minority class.
result KDE-based resampling outperforms other techniques in F1-score and G-mean.
Paper improves transaction-based Ponzi detection on Ethereum.
problem Low accuracy of current transaction-based Ponzi detection models.
method Employ time-series features to improve accuracy.
result Up to 30% higher F1-scores achieved with new features.
Study develops and improves risk models using machine learning methods.
problem Classifying business delinquency using machine learning.
method Exploring several machine learning methods including regularization, hyper-parameter optimization, and model ensembling.
result Bagging on KNN with K=9 is the optimal model for risk classification.
Machine learning models show intermarket data can predict stock market performance better than expected.
problem Evaluating the semi-strong form of the Efficient Market Hypothesis.
method Used machine learning techniques on various intermarket data sets to predict stock market performance.
result Intermarket data significantly outperforms baselines in predicting stock market movement, contradicting the semi-strong EMH.
The paper benchmarks data stream classifiers for human activity recognition on connected devices.
problem Challenges in human activity recognition on connected devices, particularly high memory consumption and low F1 scores.
method Evaluation of five stream classification algorithms on real and synthetic datasets, measuring both performance and resource consumption.
result HT and MF classifiers show superior performance and resilience to concept drift compared to other algorithms.
DeepCapture detects image spam emails using CNN and data augmentation.
problem Detecting new image spam emails with overfitting.
method CNN-XGBoost framework with data augmentation.
result DeepCapture achieves an F1-score of 88%.
Graph Unlearningcs.LG
GraphEraser improves unlearning efficiency for graph data.
problem Improving unlearning efficiency for graph data.
method Two novel graph partition algorithms and a learning-based aggregation method.
result Achieves up to 35.94× unlearning time improvement on large datasets.