# Class Imbalance

Training data for wearable fall detection is compressed into a very small class-balanced synthetic set. Earlier pipelines either used hand-crafted features with shallow classifiers or trained deep networks on the full imbalanced corpus with re-sampling, at high data and compute cost. FallNest aligns synthetic and real samples in both time and frequency domains through gradient direction and embedding distribution, initialized by class-balanced K-Means and augmented with multi-view Fourier views. On SisFall, KFall and MobiFall under subject-wise splits with naturally imbalanced test sets, a 102K-parameter TinyCNN trained on only 32 to 146 synthetic windows reaches 93.5 to 95.8 percent mean accuracy and 0.89 to 0.98 PR-AUC over five seeds.

Training data for wearable fall detection is compressed into a very small class-balanced synthetic set. Earlier pipelines either used hand-crafted features with shallow classifiers or trained deep networks on the full imbalanced corpus with re-sampling, at high data and compute cost. FallNest aligns synthetic and real samples in both time and frequency domains through gradient direction and embedding distribution, initialized by class-balanced K-Means and augmented with multi-view Fourier views. On SisFall, KFall and MobiFall under subject-wise splits with naturally imbalanced test sets, a 102K-parameter TinyCNN trained on only 32 to 146 synthetic windows reaches 93.5 to 95.8 percent mean accuracy and 0.89 to 0.98 PR-AUC over five seeds.

The work first links data augmentation to federated learning convergence behavior, showing that reducing label proportion imbalance accelerates convergence, and then proposes DAFL: with clients' class counts known, the server assigns the minimum augmentation per client-class pair by minimizing augmentation and training time while constraining global class imbalance; on six imbalanced configurations of CIFAR-10 with eight classes and eight clients, DAFL achieves higher minority-class F1 with shorter training time on D2, D4, D5, and D6, reaching minority-class F1 0.183±0.055 and convergence time 188.119±86.344 s on D2, outperforming FedProx and Focal Loss.

The work first links data augmentation to federated learning convergence behavior, showing that reducing label proportion imbalance accelerates convergence, and then proposes DAFL: with clients' class counts known, the server assigns the minimum augmentation per client-class pair by minimizing augmentation and training time while constraining global class imbalance; on six imbalanced configurations of CIFAR-10 with eight classes and eight clients, DAFL achieves higher minority-class F1 with shorter training time on D2, D4, D5, and D6, reaching minority-class F1 0.183±0.055 and convergence time 188.119±86.344 s on D2, outperforming FedProx and Focal Loss.

Analyzing the intrinsic difficulty of delay detection across 14 public event logs, the study finds that remaining times are strongly right-skewed, that existing LSTM models capture the mode of the distribution but perform poorly on high-delay cases, and that prediction error and prediction-interval width both grow with true remaining time (positive in 10 of 14 logs); it then evaluates imbalanced regression approaches (SMOGN resampling, CSW, BMSE, EAL, SERA) with only limited benefit, and instead feeds uncertainty features from a survival model (prediction standard deviation, 80% and 90% prediction-interval widths, tail mass, and temporal context) into a CatBoost classifier for binary delay detection, raising average recall from 0.21 to 0.61 at the q=0.

Analyzing the intrinsic difficulty of delay detection across 14 public event logs, the study finds that remaining times are strongly right-skewed, that existing LSTM models capture the mode of the distribution but perform poorly on high-delay cases, and that prediction error and prediction-interval width both grow with true remaining time (positive in 10 of 14 logs); it then evaluates imbalanced regression approaches (SMOGN resampling, CSW, BMSE, EAL, SERA) with only limited benefit, and instead feeds uncertainty features from a survival model (prediction standard deviation, 80% and 90% prediction-interval widths, tail mass, and temporal context) into a CatBoost classifier for binary delay detection, raising average recall from 0.21 to 0.61 at the q=0.

The study collected user reviews of the EV Charging/SPKLU feature in PLN Mobile from Google Play Store, labeled sentiment using ratings as weak labels, applied algorithm-specific class weighting on the training data to address class imbalance, and compared seven classifiers—Logistic Regression, SVM, Naive Bayes, MLP, RNN, BiLSTM, and DistilBERT—finding that MLP achieved the highest validation macro F1 (67.80%) and was selected for final testing, where it reached 89.16% accuracy and 59.42% macro F1 on 286 test instances, indicating high overall classification performance with uneven performance across sentiment classes.

The study collected user reviews of the EV Charging/SPKLU feature in PLN Mobile from Google Play Store, labeled sentiment using ratings as weak labels, applied algorithm-specific class weighting on the training data to address class imbalance, and compared seven classifiers—Logistic Regression, SVM, Naive Bayes, MLP, RNN, BiLSTM, and DistilBERT—finding that MLP achieved the highest validation macro F1 (67.80%) and was selected for final testing, where it reached 89.16% accuracy and 59.42% macro F1 on 286 test instances, indicating high overall classification performance with uneven performance across sentiment classes.

The work shows that semi-supervised domain generalization methods such as FBCSA and DGWM degrade substantially under long-tailed class distributions, and proposes IMaX: maximizing the mutual information between learned features and latent labels under supervision constraints from labeled samples, while replacing the standard marginal entropy term with a Tsallis α-entropy to relax the class-balance assumption; across two modalities (ESCA histopathology and diabetic retinopathy grading), three SSL frameworks and three SSDG methods, IMaX improves accuracy in all but one setting, with gains up to 7.3 points in the low-label regime (mL=5).

The work shows that semi-supervised domain generalization methods such as FBCSA and DGWM degrade substantially under long-tailed class distributions, and proposes IMaX: maximizing the mutual information between learned features and latent labels under supervision constraints from labeled samples, while replacing the standard marginal entropy term with a Tsallis α-entropy to relax the class-balance assumption; across two modalities (ESCA histopathology and diabetic retinopathy grading), three SSL frameworks and three SSDG methods, IMaX improves accuracy in all but one setting, with gains up to 7.3 points in the low-label regime (mL=5).