World PulseNow
Newsletter

Multiplicative Reweighting for Robust Neural Network Optimization

arXiv — cs.LG•Wednesday, November 12, 2025 at 5:00:00 AM
PositiveArtificial Intelligence
The introduction of Multiplicative Reweighting (MW) for neural network optimization addresses a critical challenge: the degradation of model performance due to noisy labels during training. By leveraging principles from learning with expert advice, MW updates have been theoretically established to converge when used with gradient descent, proving advantageous in one-dimensional cases. Empirical validation on datasets such as CIFAR-10, CIFAR-100, and Clothing1M reveals that MW significantly enhances the accuracy of neural networks in the presence of label noise. Furthermore, the method shows promise in improving adversarial robustness, which is increasingly vital in the context of machine learning applications facing real-world data challenges. This advancement not only contributes to the field of artificial intelligence but also sets a foundation for more resilient neural network architectures in various applications.
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Recommended Readings
Networks with Finite VC Dimension: Pro and Contra
arXiv — stat.ML19 hours ago
Networks with Finite VC Dimension: Pro and Contra
NeutralArtificial Intelligence
The article explores the approximation and learning capabilities of neural networks in relation to their VC dimension, focusing on high-dimensional geometry and statistical learning theory. It highlights that while a finite VC dimension is beneficial for uniform convergence of empirical errors, it may not be ideal for approximating functions from a probability distribution relevant to specific applications. The study demonstrates that errors in approximation and empirical errors behave almost deterministically for networks with finite VC dimensions when processing large datasets.
Read full article
via arXiv — stat.ML
Enhanced Structured Lasso Pruning with Class-wise Information
arXiv — cs.CV2 days ago
Enhanced Structured Lasso Pruning with Class-wise Information
PositiveArtificial Intelligence
The paper titled 'Enhanced Structured Lasso Pruning with Class-wise Information' discusses advancements in neural network pruning methods. Traditional pruning techniques often overlook class-wise information, leading to potential loss of statistical data. This study introduces two new pruning schemes, sparse graph-structured lasso pruning with Information Bottleneck (sGLP-IB) and sparse tree-guided lasso pruning with Information Bottleneck (sTLP-IB), aimed at preserving statistical information while reducing model complexity.
Read full article
via arXiv — cs.CV
AMUN: Adversarial Machine UNlearning
arXiv — cs.LG2 days ago
AMUN: Adversarial Machine UNlearning
PositiveArtificial Intelligence
The paper titled 'AMUN: Adversarial Machine UNlearning' discusses a novel method for machine unlearning, which allows users to delete specific datasets to comply with privacy regulations. Traditional exact unlearning methods require significant computational resources, while approximate methods have not achieved satisfactory accuracy. The proposed Adversarial Machine UNlearning (AMUN) technique enhances model performance by fine-tuning on adversarial examples, effectively reducing model confidence on forgotten samples while maintaining accuracy on test datasets.
Read full article
via arXiv — cs.LG
Orthogonal Soft Pruning for Efficient Class Unlearning
arXiv — cs.LG2 days ago
Orthogonal Soft Pruning for Efficient Class Unlearning
PositiveArtificial Intelligence
The article discusses FedOrtho, a federated unlearning framework designed to enhance data unlearning in federated learning environments. It addresses the challenges of balancing forgetting and retention, particularly in non-IID settings. FedOrtho employs orthogonalized deep convolutional kernels and a one-shot soft pruning mechanism, achieving state-of-the-art performance on datasets like CIFAR-10 and TinyImageNet, with over 98% forgetting quality and 97% retention accuracy.
Read full article
via arXiv — cs.LG
destroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity
arXiv — cs.CL2 days ago
destroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity
NeutralArtificial Intelligence
The paper titled 'destroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity' discusses advancements in machine learning and neural networks, particularly in natural language processing. It highlights the vulnerabilities of machine learning models and proposes a novel adversarial attack strategy that generates ambiguous inputs to confuse these models. The research aims to enhance the robustness of machine learning systems by developing adversarial instances with maximum perplexity.
Read full article
via arXiv — cs.CL
UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations
arXiv — cs.CV2 days ago
UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations
PositiveArtificial Intelligence
Unified Heterogeneous Knowledge Distillation (UHKD) is a proposed framework that enhances knowledge distillation (KD) by utilizing intermediate features in the frequency domain. This approach addresses the limitations of traditional KD methods, which are primarily designed for homogeneous models and struggle in heterogeneous environments. UHKD aims to improve model compression while maintaining accuracy, making it a significant advancement in the field of artificial intelligence.
Read full article
via arXiv — cs.CV
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
arXiv — cs.LG2 days ago
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
PositiveArtificial Intelligence
The paper titled 'On the Necessity of Output Distribution Reweighting for Effective Class Unlearning' identifies a critical flaw in class unlearning evaluations, specifically the neglect of class geometry, which can lead to privacy breaches. It introduces a membership-inference attack via nearest neighbors (MIA-NN) to identify unlearned samples. The authors propose a new fine-tuning objective that adjusts the model's output distribution to mitigate privacy risks, demonstrating that existing unlearning methods are susceptible to MIA-NN across various datasets.
Read full article
via arXiv — cs.LG
PrivDFS: Private Inference via Distributed Feature Sharing against Data Reconstruction Attacks
arXiv — cs.LG2 days ago
PrivDFS: Private Inference via Distributed Feature Sharing against Data Reconstruction Attacks
PositiveArtificial Intelligence
The paper introduces PrivDFS, a distributed feature-sharing framework designed for input-private inference in image classification. It addresses vulnerabilities in split inference that allow Data Reconstruction Attacks (DRAs) to reconstruct inputs with high fidelity. By fragmenting the intermediate representation and processing these fragments independently across a majority-honest set of servers, PrivDFS limits the reconstruction capability while maintaining accuracy within 1% of non-private methods.
Read full article
via arXiv — cs.LG