World PulseNow
Newsletter

Multivariate Variational Autoencoder

arXiv — cs.LG•Wednesday, November 12, 2025 at 5:00:00 AM
PositiveArtificial Intelligence
The introduction of the Multivariate Variational Autoencoder (MVAE) marks a significant advancement in the field of artificial intelligence, particularly in variational inference. By preserving Gaussian tractability while lifting the diagonal posterior restriction, MVAE enhances the modeling of complex data distributions. It achieves this through a unique factorization of posterior covariance, employing a global coupling matrix to induce correlations across the dataset and per-sample diagonal scales to manage local uncertainties. Experimental results on popular datasets such as MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 reveal that MVAE consistently matches or improves upon the reconstruction quality of traditional diagonal-covariance VAEs, while also delivering robust gains in calibration and unsupervised structure. The latent-plane visualizations further illustrate the model's ability to produce smoother traversals and sharper local details. To facilitate further research and comp…
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Recommended Readings
Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning
arXiv — cs.CV2 days ago
Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning
PositiveArtificial Intelligence
The paper titled 'Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning' addresses the challenges of class-incremental learning (CIL) in vision-language models like CLIP. It introduces a two-stage framework called DMC, which separates the adaptation of the vision encoder from the optimization of textual soft prompts. This approach aims to mitigate classifier bias and maintain cross-modal alignment, enhancing the model's ability to learn new categories without forgetting previously acquired knowledge.
Read full article
via arXiv — cs.CV
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
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
Inferring response times of perceptual decisions with Poisson variational autoencoders
arXiv — cs.LG2 days ago
Inferring response times of perceptual decisions with Poisson variational autoencoders
PositiveArtificial Intelligence
The article presents a model for perceptual decision-making using Poisson variational autoencoders, which captures the temporal dynamics of decision processes. Unlike traditional models that treat decisions as instantaneous, this approach incorporates sensory encoding and Bayesian decoding of neural spiking activity. The model is capable of generating trial-by-trial patterns of choices and response times, demonstrating its effectiveness in replicating key empirical signatures of perceptual decision-making.
Read full article
via arXiv — cs.LG
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