Deep Neural Networks with Ordinal Loss for Medical Applications

In many prediction problems in medical applications, target labels exhibit an inherent ordinal structure, where class ordering reflects clinically meaningful severity levels. The cost associated with misclassification is often non-uniform and asymmetric, as errors between distant ordinal categories may have substantially more severe consequences than errors between adjacent ones, and overestimating disease severity may have different clinical implications than underestimating it. Traditional loss functions such as multi-class cross-entropy treat all misclassifications equally and fail to incorporate this ordering information. Recent advances in ordinal regression aim to address this limitation by integrating rank-based structures into deep learning models. In this work, we introduce the \textbf{Ordinal Cross-Entropy (OCE)} framework, a general and architecture-independent approach for learning from ordinal data. The proposed method extends the standard cross-entropy formulation to account for misclassification severity through an ordinal cost matrix while preserving the probabilistic interpretation and optimization benefits of the conventional loss. We provide a theoretical analysis of the OCE gradient behavior and show that it yields smoother optimization dynamics and improved ordinal consistency. Experiments on benchmark datasets show that our method achieves lower prediction error costs and better calibration compared to existing state-of-the-art ordinal approaches, establishing OCE as a simple yet effective solution for ordinal regression in deep neural networks.

Complementary Attention Head Pruning for Efficient Transformers

The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments. While structured pruning offers a pathway to compression, existing state-of-the-art methods often rely on gradient-based importance ranking or stochastic gating, which suffer from instability, structural degeneration, and the need for extensive manual hyperparameter tuning. In this paper, we introduce CAHP (Complementary Attention Head Pruning), a novel post-hoc framework that redefines head selection as a global graph-theoretical problem. Rather than evaluating heads in isolation, CAHP utilizes graph-based clustering combined with information-theoretic distance measures to identify and preserve a topologically diverse subset of complementary attention heads. Without requiring a predefined sparsity level or pruning ratio, the framework automatically determines the number of selected attention heads across layers by identifying a diminishing marginal performance curve, where pruning additional heads leads to a sharp degradation in performance, as determined by the chosen polynomial degree. Extensive evaluations on the SST-5 and MNLI benchmarks, across different Transformer model scales, demonstrate that CAHP consistently outperforms competitive baselines, particularly in high-compression regimes. Furthermore, our structural analysis shows that CAHP avoids the "proximity bias" of gradient-based pruning methods, which tend to preserve heads mainly in layers close to the output, and instead retains a functionally critical set of attention heads in the model's intermediate layers.

Automatic Complementary Separation Pruning Toward Lightweight CNNs

In this paper, we present Automatic Complementary Separation Pruning (ACSP), a novel and fully automated pruning method for convolutional neural networks. ACSP integrates the strengths of both structured pruning and activation-based pruning, enabling the efficient removal of entire components such as neurons and channels while leveraging activations to identify and retain the most relevant components. Our approach is designed specifically for supervised learning tasks, where we construct a graph space that encodes the separation capabilities of each component with respect to all class pairs. By employing complementary selection principles and utilizing a clustering algorithm, ACSP ensures that the selected components maintain diverse and complementary separation capabilities, reducing redundancy and maintaining high network performance. The method automatically determines the optimal subset of components in each layer, utilizing a knee-finding algorithm to select the minimal subset that preserves performance without requiring user-defined pruning volumes. Extensive experiments on multiple architectures, including VGG-16, ResNet-50, and MobileNet-V2, across datasets like CIFAR-10, CIFAR-100, and ImageNet-1K, demonstrate that ACSP achieves competitive accuracy compared to other methods while significantly reducing computational costs. This fully automated approach not only enhances scalability but also makes ACSP especially practical for real-world deployment by eliminating the need for manually defining the pruning volume.

Graph-Based Automatic Feature Selection for Multi-Class Classification via Mean Simplified Silhouette

This paper introduces a novel graph-based filter method for automatic feature selection (abbreviated as GB-AFS) for multi-class classification tasks. The method determines the minimum combination of features required to sustain prediction performance while maintaining complementary discriminating abilities between different classes. It does not require any user-defined parameters such as the number of features to select. The methodology employs the Jeffries-Matusita (JM) distance in conjunction with t-distributed Stochastic Neighbor Embedding (t-SNE) to generate a low-dimensional space reflecting how effectively each feature can differentiate between each pair of classes. The minimum number of features is selected using our newly developed Mean Simplified Silhouette (abbreviated as MSS) index, designed to evaluate the clustering results for the feature selection task. Experimental results on public data sets demonstrate the superior performance of the proposed GB-AFS over other filter-based techniques and automatic feature selection approaches. Moreover, the proposed algorithm maintained the accuracy achieved when utilizing all features, while using only $7\%$ to $30\%$ of the features. Consequently, this resulted in a reduction of the time needed for classifications, from $15\%$ to $70\%$.

Graph-based Extreme Feature Selection for Multi-class Classification Tasks

When processing high-dimensional datasets, a common pre-processing step is feature selection. Filter-based feature selection algorithms are not tailored to a specific classification method, but rather rank the relevance of each feature with respect to the target and the task. This work focuses on a graph-based, filter feature selection method that is suited for multi-class classifications tasks. We aim to drastically reduce the number of selected features, in order to create a sketch of the original data that codes valuable information for the classification task. The proposed graph-based algorithm is constructed by combing the Jeffries-Matusita distance with a non-linear dimension reduction method, diffusion maps. Feature elimination is performed based on the distribution of the features in the low-dimensional space. Then, a very small number of feature that have complementary separation strengths, are selected. Moreover, the low-dimensional embedding allows to visualize the feature space. Experimental results are provided for public datasets and compared with known filter-based feature selection techniques.

Adaptive Learning for the Resource-Constrained Classification Problem

Resource-constrained classification tasks are common in real-world applications such as allocating tests for disease diagnosis, hiring decisions when filling a limited number of positions, and defect detection in manufacturing settings under a limited inspection budget. Typical classification algorithms treat the learning process and the resource constraints as two separate and sequential tasks. Here we design an adaptive learning approach that considers resource constraints and learning jointly by iteratively fine-tuning misclassification costs. Via a structured experimental study using a publicly available data set, we evaluate a decision tree classifier that utilizes the proposed approach. The adaptive learning approach performs significantly better than alternative approaches, especially for difficult classification problems in which the performance of common approaches may be unsatisfactory. We envision the adaptive learning approach as an important addition to the repertoire of techniques for handling resource-constrained classification problems.

Adaptive Cost-Sensitive Learning in Neural Networks for Misclassification Cost Problems

We design a new adaptive learning algorithm for misclassification cost problems that attempt to reduce the cost of misclassified instances derived from the consequences of various errors. Our algorithm (adaptive cost sensitive learning - AdaCSL) adaptively adjusts the loss function such that the classifier bridges the difference between the class distributions between subgroups of samples in the training and test data sets with similar predicted probabilities (i.e., local training-test class distribution mismatch). We provide some theoretical performance guarantees on the proposed algorithm and present empirical evidence that a deep neural network used with the proposed AdaCSL algorithm yields better cost results on several binary classification data sets that have class-imbalanced and class-balanced distributions compared to other alternative approaches.