Institution profile

Universidade Federal da Bahia

Academic institutionsouthamerica · br
Official website
Research library32linked papers
Opportunities0open roles
Selected work

Representative Papers

Sparse Principal Component Analysis via Wavelets for Distributed Data

Aug 05, 2026

This work addresses the challenges of statistical inconsistency, high communication overhead, and privacy concerns in traditional principal component analysis (PCA) when applied to high-dimensional distributed data. The authors propose a novel distributed PCA framework that incorporates wavelet-based sparsification, leveraging wavelet transforms to obtain sparse representations of variables. By integrating this sparsification with a distributed optimization algorithm, the method efficiently estimates the global shared subspace without requiring raw data aggregation. The approach preserves statistical consistency while substantially reducing communication costs. Experimental results demonstrate that, for dimensions \(d \geq 152\), the proposed method consistently outperforms existing approaches in both estimation accuracy and the number of transmitted coefficients.

0 citationsRead paper

SILVA Networks as Structured Implicit Layers and Vector Attractors via Dynamic Interaction Fields

Jul 30, 2026

Existing implicit neural layers struggle to disentangle the distinct contributions of input stimuli, local propagation, global context, and solver dynamics to the learned representations. This work proposes SILVA, a unified fixed-point architecture that explicitly decouples stimulus injection, local and global interactions, damping, and readout mechanisms. Through domain-adaptive designs of node, neighborhood, and global summarization modules, SILVA is tailored for diverse tasks spanning images, molecular graphs, citation networks, and long-range graph problems. As the first method to structurally decompose multi-source interactions within implicit layers, SILVA renders internal dynamics trainable, ablatable, and visualizable. Experiments reveal that graph tasks predominantly rely on local interactions, MNIST exhibits limited recursive gains under high capacity, and long-range node classification significantly benefits from explicitly modeled global interactions.

0 citationsRead paper
Recent publications

Latest Papers

Sparse Principal Component Analysis via Wavelets for Distributed Data

Aug 05, 2026

This work addresses the challenges of statistical inconsistency, high communication overhead, and privacy concerns in traditional principal component analysis (PCA) when applied to high-dimensional distributed data. The authors propose a novel distributed PCA framework that incorporates wavelet-based sparsification, leveraging wavelet transforms to obtain sparse representations of variables. By integrating this sparsification with a distributed optimization algorithm, the method efficiently estimates the global shared subspace without requiring raw data aggregation. The approach preserves statistical consistency while substantially reducing communication costs. Experimental results demonstrate that, for dimensions \(d \geq 152\), the proposed method consistently outperforms existing approaches in both estimation accuracy and the number of transmitted coefficients.

0 citationsRead paper

SILVA Networks as Structured Implicit Layers and Vector Attractors via Dynamic Interaction Fields

Jul 30, 2026

Existing implicit neural layers struggle to disentangle the distinct contributions of input stimuli, local propagation, global context, and solver dynamics to the learned representations. This work proposes SILVA, a unified fixed-point architecture that explicitly decouples stimulus injection, local and global interactions, damping, and readout mechanisms. Through domain-adaptive designs of node, neighborhood, and global summarization modules, SILVA is tailored for diverse tasks spanning images, molecular graphs, citation networks, and long-range graph problems. As the first method to structurally decompose multi-source interactions within implicit layers, SILVA renders internal dynamics trainable, ablatable, and visualizable. Experiments reveal that graph tasks predominantly rely on local interactions, MNIST exhibits limited recursive gains under high capacity, and long-range node classification significantly benefits from explicitly modeled global interactions.

0 citationsRead paper