Publicações em Inglês
-
Dissertação - Bridging the Gap: A Systematic Framework for Benchmarking Graph Neural Networks
Autor: Willian Borges de Lemos (Currículo Lattes)
ResumoThe exponential growth of data has presented both opportunities and challenges for organizations and individuals seeking to extract meaningful insights and patterns. In recent years, the field of complex network analysis has gained increasing attention as a solution to identifying patterns and structures in graphs. Graph embedding is a necessary step to bridge the gap between graph data and machine learning algorithms, allowing for the efficient processing and analysis of graph structures. However, the field of graph embedding remains fragmented, with a lack of a consensual theoretical understanding and a unified framework to describe and compare different techniques. This work aims to address these issues by providing a overview of the current state of the art in graph embedding and its influence on complex network analysis. The paper develops a unified framework for describing and comparing various graph embedding techniques, highlighting the strengths and weaknesses of each approach on common factors.
Palavras-chave: Deep Learning; Graph Embedding; Graph Neural Networks; Matrix Factorization
-
Dissertação - Resource Profiling in the Training of Graph Neural Networks
Autor: Lucas de Angelo Martins Ribeiro (Currículo Lattes)
ResumoGraph processing can be applied in various areas of society, technology, industry, and science to extract knowledge from real-world data. With the growth in the understanding and application of Artificial Intelligence, derived fields have emerged to explore the application of graphs using intelligent mechanisms, such as recommendation systems, social networks, among others. In this context, numerous models and frameworks for Graph Neural Networks have emerged, expanding the capabilities of these mechanisms. Despite significant advances in the study of Graph Neural Networks aimed at achieving better accuracy in models, the analysis of resources for processing these models is still an area that can be further explored to gain a deeper understanding of these systems from an architectural and execution environment perspective. In this work, a quantitative analysis of hardware resource consumption during the training phase of graph neural networks was conducted, taking into account potential benefits from using GPU accelerators when evaluating datasets of different compositions. The GCN and GraphSAGE models were used as the subject of study in this work, with implementations in the PyTorch Geometric framework. As a result, a significant improvement in the processing time of these models was observed when GPU accelerators were used, along with significant variations in the points of high resource utilization. It was also noted that datasets with different structural compositions (e.g., the number of edges and average node degree) can also exhibit significant variations in results.
Palavras-chave: Graph Neural Networks, Graph Processing, Data management, Parallel Processing, System performance analysis
-
Dissertação - The not-so-easy task of taking heavy-lift ML models to the edge: a performance-watt perspective
Autor: Lucas Caetano Meireles Pereira (Currículo Lattes)
ResumoEdge computing is a new development paradigm that brings computational power to the network edge through novel intelligent end-user services. It allows latency-sensitive applications to be placed where the data is created, thus reducing communication overhead and improving security, mobility and power consumption. There is a plethora of applications benefiting from this type of processing. Of particular interest is emerging edge-based image classification at the microscopic level. The scale and magnitude of the objects to segment, detect and classify are very challenging, with data collected using order of magnitude in magnification. The required data processing is intense, and the wish list of end-users in this space includes tools and solutions that fit into a small device. Taking heavy-lift classification models initially built in the cloud to desk-based image analysis devices is a hard job for application developers. This work looks at the performance limitations and energy consumption footprint in embedding deep learning classification models in a representative edge computing device. Particularly, the dataset and heavy-lift models explored in the case study are phytoplankton images to detect Harmful Algae Blooms (HAB) in aquaculture at early stages. The work takes a deep learning models trained for phytoplankton classification and deploys it at the edge. The embedded model, deployed in a base form alongside optimised options, is submitted to a series of system stress experiments. The performance and power consumption profiling help understand system limitations and their impact on the microscopic grade image classification task.
Palavras-chave: Edge Computing, Artificial Intelligence, Phytoplankton
-
Dissertação - Soybean Weeds Segmentation using VT-Net: a Convolutional-Transformer Model
Autor: Lucas de Souza Silva (Currículo Lattes)
Dissertação - Soybean Weeds Segmentation using VT-Net: a Convolutional-Transformer Model
-
Dissertação - Trajectory planning of an aerial-underwater hybrid vehicle based on heuristics for energy efficiency (2023)
Autor: Pedro Miranda Pinheiro (Currículo Lattes)
Dissertação - Trajectory planning of an aerial-underwater hybrid vehicle based on heuristics for...
-
Dissertação - Generalizations of the Choquet Integral Applied to Classification and Decision Making Problems (2021)
Autor: Jonata Cristian Wieczynski (Currículo Lattes)
Dissertação - Generalizations of the Choquet Integral Applied to Classification and Decision...