Kleyton da Costa

To imagine is the characteristic act, not of the poet’s mind, or the painter’s, or the scientist’s, but of the mind of man.
(The Ascent of Man by Jacob Bronowski)

I am pursuing an MSc in Computer Science at PUC-Rio, under the supervision of Prof. Hélio Côrtes Vieira Lopes. In addition, I work as an AI Researcher at Holistic AI in London, UK, and as a Research Engineer at ExACTa. Furthermore, I am a core contributor to the open-source project quantsci, where I focus on develop tools for science and engineering projects.

My research interests include (and is not limited to):

Learning on Graphs
Responsible AI
Algorithms for Optimization

The best way to contact me is by email: kleyton.vsc@gmail.com. I’m always open to interesting discussions and collaboration opportunities. It’s possible check my research on Google Scholar.

news

Sep 24, 2024	We release the version 0.1.8 of the optymus library. New optimization examples and methods.
Jan 30, 2024	We release an updated version of the paper Evaluating explainability for machine learning predictions using model-agnostic metrics
Sep 03, 2023	Our paper Deep learning model fragility and implications for financial stability and regulation was published as Staff Working Paper of Bank of England.
Mar 10, 2023	I started my MSc in Computer Science at Pontifical Catholic University of Rio de Janeiro (PUC-Rio).

latest posts

Oct 13, 2024	High-performance derivative calculation techniques for scientific computing
Sep 10, 2024	Relation of mutual information to divergence
Mar 02, 2024	Many explanations are wrong, but some are useful

selected publications

Arxiv

Evaluating explainability for machine learning predictions using model-agnostic metrics

Cristian Munoz , Kleyton Costa , Bernardo Modenesi , and 1 more author

arXiv preprint arXiv:2302.12094, 2024

Abs PDF

Rapid advancements in artificial intelligence (AI) technology have brought about a plethora of new challenges in terms of governance and regulation. AI systems are being integrated into various industries and sectors, creating a demand from decision-makers to possess a comprehensive and nuanced understanding of the capabilities and limitations of these systems. One critical aspect of this demand is the ability to explain the results of machine learning models, which is crucial to promoting transparency and trust in AI systems, as well as fundamental in helping machine learning models to be trained ethically. In this paper, we present novel metrics to quantify the degree of which AI model predictions can be easily explainable by its features. Our metrics summarize different aspects of explainability into scalars, providing a more comprehensive understanding of model predictions and facilitating communication between decision-makers and stakeholders, thereby increasing the overall transparency and accountability of AI systems.
Bank of England

Deep learning model fragility and implications for financial stability and regulation

Rishabh Kumar , Adriano Koshiyama , Kleyton Costa , and 6 more authors

2023

Abs PDF

Deep learning models are being utilised increasingly within finance. Given the models are opaque in nature and are now being deployed for internal and consumer facing decisions, there are increasing concerns around the trustworthiness of their results. We test the stability of predictions and explanations of different deep learning models, which differ between each other only via subtle changes to model settings, with each model trained over the same data. Our results show that the models produce similar predictions but different explanations, even when the differences in model architecture are due to arbitrary factors like random seeds. We compare this behaviour with traditional, interpretable, ’glass-box models’, which show similar accuracies while maintaining stable explanations and predictions. Finally, we show a methodology based on network analysis to compare deep learning models. Our analysis has implications for the adoption and risk management of future deep learning models by regulated institutions.