Research

My research focuses on large-scale graph processing and mining. I develop systems and algorithms that handle massive networks efficiently, working at the intersection of high-performance computing, big data, and machine learning applied to graphs.

I design distributed and parallel systems for processing graphs at scale, including frameworks for clusters, GPUs, and heterogeneous environments. Students work on projects such as implementing efficient GPU kernels for subgraph mining, developing graph neural network architectures for pattern recognition, integrating LLMs with graph structures for question-answering systems, and optimizing distributed graph processing frameworks. My work applies to social network analysis, biological networks, knowledge graphs, and fraud detection.

Student Opportunities

I am seeking students to work on graph processing, machine learning on graphs, GPU acceleration, and distributed systems. Students work with tools like CUDA, PyTorch, Apache Spark, and graph processing frameworks, gaining experience in parallel programming, algorithm design, and performance optimization.

I look for strong programming skills (Java, C++, Python, or CUDA) and interest in algorithms and systems. If interested, send me an email with your CV and research interests.

Current Students

• Bruna Galdêncio [masters] — georeferenced data, nature-based solutions, graph learning
• Diogo Carvalho [undergrad] — subgraph optimization, parallel computation
• Jean Diniz [undergrad] — LLM, RAG, Graph RAG, document search
• Paulo Carvalho [undergrad] — LLM, text-to-graph, experimental evaluation
• Nathan Pereira [undergrad] — graph modeling, graph and LLM powered question-answer
• Davi Miranda [undergrad] — code generation applied to subgraph optimization
• Helio Silva [undergrad] — compression, data structures, biological graphs