Amauri Holanda Souza Junior
Research Subjects
Amauri Holanda Souza Junior has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Joao Paulo Pordeus Gomes
Federal University of Ceará
5 shared publications - Cesar Lincoln Cavalcante Mattos
Universidade Federal do Ceará
2 shared publications - Francesco Corona
Aalto University
2 shared publications - Joonas Hämäläinen
University of Jyväskylä
2 shared publications - Tamara Arruda Pereira
Federal Institute of Ceara
2 shared publications - Tommi Kärkkäinen
University of Jyväskylä
2 shared publications
Latest Publications
- Open Access
- 25 November 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (12) , 289
Minimal learning machine for multi-label learning
Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. In addition to its simplicity, the proposed method is fully deterministic: Its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess the uncertainty of the predictions for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.
- 25 November 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (12) , 289
Open AccessMinimal learning machine for multi-label learning
Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. In addition to its simplicity, the proposed method is fully deterministic: Its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess the uncertainty of the predictions for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.
- Open Access
- 17 November 2024
- Published by Sociedade Brasileira de Computação
- p. 137-144
Simplifying Simplex Convolutional Networks
Topological deep learning (TDL) has recently emerged as a family of neural networks for data on topological domains (e.g., graphs and cellular complexes). In the context of graph data, TDL provides a recipe for leveraging high-order information, e.g., from cliques, to boost the expressiveness of graph neural networks. This additional power comes at a computational cost, stemming from message passing between higher-order structures. In this paper, we alleviate the computing toll of TDL by proposing SimpleXCN, a linear convolutional model for simplicial complexes. SimpleXCN derives naturally from removing non-linearities of base TDL architectures. Despite its simplicity, SimpleXCN remains competitive with established topological neural networks in node classification tasks. Our experiments show a reduction of approximately 25% in time and 10 times in the number of parameters, and consequently a significant reduction in memory usage of up to 50% compared to other SNNs.
- 17 November 2024
- Published by Sociedade Brasileira de Computação
- p. 137-144
Open AccessSimplifying Simplex Convolutional Networks
Topological deep learning (TDL) has recently emerged as a family of neural networks for data on topological domains (e.g., graphs and cellular complexes). In the context of graph data, TDL provides a recipe for leveraging high-order information, e.g., from cliques, to boost the expressiveness of graph neural networks. This additional power comes at a computational cost, stemming from message passing between higher-order structures. In this paper, we alleviate the computing toll of TDL by proposing SimpleXCN, a linear convolutional model for simplicial complexes. SimpleXCN derives naturally from removing non-linearities of base TDL architectures. Despite its simplicity, SimpleXCN remains competitive with established topological neural networks in node classification tasks. Our experiments show a reduction of approximately 25% in time and 10 times in the number of parameters, and consequently a significant reduction in memory usage of up to 50% compared to other SNNs.
- 19 November 2022
- Published by Springer Nature
- p. 588-600
ConveXplainer for Graph Neural Networks
- Open Access
Rethinking pooling in graph neural networks
Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Strikingly, our experiments demonstrate that using these variants does not result in any decrease in performance. To understand this phenomenon, we study the interplay between convolutional layers and the subsequent pooling ones. We show that the convolutions play a leading role in the learned representations. In contrast to the common belief, local pooling is not responsible for the success of GNNs on relevant and widely-used benchmarks.
Open AccessRethinking pooling in graph neural networks
Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Strikingly, our experiments demonstrate that using these variants does not result in any decrease in performance. To understand this phenomenon, we study the interplay between convolutional layers and the subsequent pooling ones. We show that the convolutions play a leading role in the learned representations. In contrast to the common belief, local pooling is not responsible for the success of GNNs on relevant and widely-used benchmarks.
- Open Access
Minimal Learning Machine: Theoretical Results and Clustering-Based Reference Point Selection
The Minimal Learning Machine (MLM) is a nonlinear supervised approach based on learning a linear mapping between distance matrices computed in the input and output data spaces, where distances are calculated using a subset of points called reference points. Its simple formulation has attracted several recent works on extensions and applications. In this paper, we aim to address some open questions related to the MLM. First, we detail theoretical aspects that assure the interpolation and universal approximation capabilities of the MLM, which were previously only empirically verified. Second, we identify the task of selecting reference points as having major importance for the MLM's generalization capability. Several clustering-based methods for reference point selection in regression scenarios are then proposed and analyzed. Based on an extensive empirical evaluation, we conclude that the evaluated methods are both scalable and useful. Specifically, for a small number of reference points, the clustering-based methods outperformed the standard random selection of the original MLM formulation.
Open AccessMinimal Learning Machine: Theoretical Results and Clustering-Based Reference Point Selection
The Minimal Learning Machine (MLM) is a nonlinear supervised approach based on learning a linear mapping between distance matrices computed in the input and output data spaces, where distances are calculated using a subset of points called reference points. Its simple formulation has attracted several recent works on extensions and applications. In this paper, we aim to address some open questions related to the MLM. First, we detail theoretical aspects that assure the interpolation and universal approximation capabilities of the MLM, which were previously only empirically verified. Second, we identify the task of selecting reference points as having major importance for the MLM's generalization capability. Several clustering-based methods for reference point selection in regression scenarios are then proposed and analyzed. Based on an extensive empirical evaluation, we conclude that the evaluated methods are both scalable and useful. Specifically, for a small number of reference points, the clustering-based methods outperformed the standard random selection of the original MLM formulation.
- Open Access
- 2 July 2017
- Published by Sociedade Brasileira de Computação
- p. 2566-2574
Uma formulação para a máquina de aprendizagem mínima baseada em programação linear
A máquina de aprendizagem mínima (MLM) é um método de aprendizado supervisionado que consiste na utilização de um mapeamento linear entre distâncias dos espaços de entrada e saída, seguido de um processo de otimização para, a partir das distâncias estimadas, estimar a saída. A etapa de teste da MLM envolve a resolução de um problema de otimização não-convexo, e pode sofrer com problemas associados a mínimos locais. Com isso em vista, neste artigo e apresentada uma formulação nessa etapa utilizando programação linear. Os experimentos mostram que o método proposto atinge desempenho semelhante aquele obtido com o algoritmo original, adicionalmente produzindo resultados com menor variância.
- 2 July 2017
- Published by Sociedade Brasileira de Computação
- p. 2566-2574
Open AccessUma formulação para a máquina de aprendizagem mínima baseada em programação linear
A máquina de aprendizagem mínima (MLM) é um método de aprendizado supervisionado que consiste na utilização de um mapeamento linear entre distâncias dos espaços de entrada e saída, seguido de um processo de otimização para, a partir das distâncias estimadas, estimar a saída. A etapa de teste da MLM envolve a resolução de um problema de otimização não-convexo, e pode sofrer com problemas associados a mínimos locais. Com isso em vista, neste artigo e apresentada uma formulação nessa etapa utilizando programação linear. Os experimentos mostram que o método proposto atinge desempenho semelhante aquele obtido com o algoritmo original, adicionalmente produzindo resultados com menor variância.
- 12 November 2015
- Published by Springer Nature
- p. 565-572
A Minimal Learning Machine for Datasets with Missing Values
- 12 November 2015
- Published by Springer Nature
- p. 565-572
A Minimal Learning Machine for Datasets with Missing Values
- 12 November 2015
- Published by Springer Nature
- p. 557-564
A Cost Sensitive Minimal Learning Machine for Pattern Classification
- 12 November 2015
- Published by Springer Nature
- p. 557-564
A Cost Sensitive Minimal Learning Machine for Pattern Classification
- 6 June 2015
- Published by Springer Nature
- p. 142-152
Ensemble of Minimal Learning Machines for Pattern Classification
- 6 June 2015
- Published by Springer Nature
- p. 142-152
Ensemble of Minimal Learning Machines for Pattern Classification
- 1 December 2013
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 46 (32) , 63-68
Spectroscopic monitoring of diesel fuels using Supervised Distance Preserving Projections
- 1 December 2013
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 46 (32) , 63-68
Spectroscopic monitoring of diesel fuels using Supervised Distance Preserving Projections