Publications

RIFF: Inducing Rules for Fraud Detection from Decision Trees

João Lucas Martins, João Bravo, Ana Sofia Gomes, Carlos Soares, Pedro Bizarro

Published at RuleML+RR 2024

Show Me What’s Wrong!: Combining Charts and Text to Guide Data Analysis

Beatriz Feliciano, Rita Costa, Jean Alves, Javier Liebana, Diogo Duarte, Pedro Bizarro

Published at NLVIZ, a workshop at IEEE VIS 2024

Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraints

Jean V. Alves, Javier Liébana, Diogo Leitão, Pedro Saleiro, Sérgio Jesus, Marco O. P. Sampaio, Mário A. T. Figueiredo, Pedro Bizarro

Published at Transactions on Machine Learning Research (07/2024)

arXiv | GitHub | PDF | YouTube

AutoVizuA11y: a Tool to Automate Screen Reader Accessibility in Charts

Diogo Duarte, Rita Costa, Pedro Bizarro, Carlos Duarte

Published at EuroVis 2024

PDF | GitHub | npm | YouTube

DiConStruct: Causal Concept-based Explanations through Black-Box Distillation

Ricardo Moreira, Jacopo Bono, Mário Cardoso, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Published at CLeaR 2024 - Conference on Causal Learning and Reasoning

On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods

Kasun Amarasinghe, Kit T. Rodolfa, Sérgio Jesus, Valerie Chen, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro, Ameet Talwalkar, Rayid Ghani

Published at AAAI-24 - Annual AAAI Conference on Artificial Intelligence

FiFAR: a fraud detection dataset for learning to defer

Jean V. Alves, Diogo Leitão, Sérgio Jesus, Marco O. P. Sampaio, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Published at ICAIF23 - Synthetic Data for AI in Finance workshop

arXiv | GitHub

Adversarial training for tabular data with attack propagation

Tiago Leon Melo, João Bravo, Marco O. P. Sampaio, Paolo Romano, Hugo Ferreira, João Tiago Ascensão, Pedro Bizarro

Published at KDD Workshop on Machine Learning in Finance 2023

The GANfather: Controllable generation of malicious activity to improve defence systems

Ricardo Ribeiro Pereira, Jacopo Bono, João Tiago Ascensão, David Aparício, Pedro Ribeiro, Pedro Bizarro

Published at Fourth ACM International Conference on AI in Finance (ICAIF23)

From random-walks to graph-sprints: a low-latency node embedding framework on continuous-time dynamic graphs

Ahmad Naser Eddin, Jacopo Bono, David Aparício, Hugo Ferreira, João Ascensão, Pedro Ribeiro, Pedro Bizarro

Published at Fourth ACM International Conference on AI in Finance (ICAIF23), KDD 2023 - Mining and Learning with Graphs workshop

arXiv | Poster | YouTube

A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies

Ada Martin, Valerie Chen, Sérgio Jesus, Pedro Saleiro

Published at ICLR 2023 workshop Trustworthy ML

Fairness-Aware Data Valuation for Supervised Learning

José Pombal, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Published at ICLR 2023 workshop Trustworthy ML

arXiv | Youtube

FairGBM: Gradient Boosting with Fairness Constraints

André F Cruz, Catarina Belém, Sérgio Jesus, João Bravo, Pedro Saleiro, Pedro Bizarro

Published at ICLR 2023, International Conference on Learning Representations

Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation

Sérgio Jesus, José Pombal, Duarte Alves, André Cruz, Pedro Saleiro, Rita P. Ribeiro, João Gama, Pedro Bizarro

Published at NeurIPS 2022

PDF | arXiv | Kaggle

LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Laundering

Mário Cardoso, Pedro Saleiro, Pedro Bizarro

Published at 3rd ACM International Conference on AI in Finance (ICAIF'22)

Lightweight Automated Feature Monitoring for Data Streams

João Conde, Ricardo Moreira, João Torres, Pedro Cardoso, Hugo Ferreira, Marco O. P. Sampaio, João Tiago Ascensão, Pedro Bizarro

Published at KDD 2022 - AutoML workshop

PDF | arXiv

Understanding Unfairness in Fraud Detection through Model and Data Bias Interactions

José Pombal, André F. Cruz, João Bravo, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Published at KDD 2022 - Machine Learning in Finance workshop

Prisoners of Their Own Devices: How Models Induce Data Bias in Performative Prediction

José Pombal, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Published at ICML 2022 - Responsible Decision Making in Dynamic Environments workshop

Human-AI Collaboration in Decision-Making: Beyond Learning to Defer

Diogo Leitão, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Published at ICML 2022 - Human-Machine Collaboration and Teaming workshop

PDF | arXiv | Poster | YouTube

A case study on implementing screen reader accessibility in dynamic visualizations

Rita Costa, Beatriz Malveiro, João Palmeiro, Pedro Bizarro

Published at EuroVis 2022

PDF | EuroVis

Data+Shift: Supporting visual investigation of data distribution shifts by data scientists

João Palmeiro, Beatriz Malveiro, Rita Costa, David Polido, Ricardo Moreira, Pedro Bizarro

Published at EuroVis 2022

PDF | EuroVis | ar5iv | YouTube

ConceptDistil: Model-Agnostic Distillation of Concept Explanations

João Bento, Ricardo Moreira, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro

Published at ICLR 2022 - PAIR2Struct workshop

PDF | arXiv

Anti-Money Laundering Alert Optimization Using Machine Learning with Graphs

Ahmad Naser Eddin, Jacopo Bono, David Aparício, David Polido, João Tiago Ascensão, Pedro Bizarro, Pedro Ribeiro

Published at AAAI - AI in Financial Services: Adaptiveness, Resilience & Governance workshop’2022

Active learning for imbalanced data under cold start

Ricardo Barata, Miguel Leite, Ricardo Pacheco, Marco O. P. Sampaio, João Tiago Ascensão, Pedro Bizarro

Published at ICAIF 2021 conference

GUDIE: A flexible, user-defined method to extract subgraphs of interest from large graphs

Maria Inês Silva, David Aparício, Beatriz Malveiro, João Tiago Ascensão, Pedro Bizarro

Published at ECML PKDD 2021 - Graph Embedding and Mining workshop

Finding NeMo: Fishing in banking networks using network motifs

Xavier Fontes, David Aparício, Maria Inês Silva, Beatriz Malveiro, João Tiago Ascensão, Pedro Bizarro

Published at VLDB 2021 - Search, Exploration, and Analysis in Heterogeneous Datastores workshop

TimeSHAP: Explaining Recurrent Models through Sequence Perturbations

João Bento, Pedro Saleiro, André Cruz, Mário A. T. Figueiredo, Pedro Bizarro

Published at KDD 2021 conference, NeurIPS 2020 - HAMLETS workshop

PDF | arXiv | GitHub | YouTube

Active learning for online training in imbalanced data streams under cold start

Ricardo Barata, Miguel Leite, Ricardo Pacheco, Marco O. P. Sampaio, João Tiago Ascensão, Pedro Bizarro

Published at KDD 2021 - Machine Learning in Finance workshop

PDF | Presentation | arXiv | YouTube

GuiltyWalker: Distance to illicit nodes in the Bitcoin network

Catarina Oliveira, João Torres, Maria Inês Silva, David Aparício, João Tiago Ascensão, Pedro Bizarro

Published at KDD 2021 - Machine Learning in Finance workshop

Weakly Supervised Multi-task Learning for Concept-based Explainability

Catarina Belém, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro

Published at ICLR 2021 - Weakly Supervised Learning workshop

PDF | arXiv | WeaSuL PDF | YouTube

Promoting Fairness through Hyperparameter Optimization

André Cruz, Pedro Saleiro, Catarina Belém, Carlos Soares, Pedro Bizarro

Published at ICDM 2021 conference, ICLR 2021 - Responsible AI workshop

PDF | arXiv | GitHub | ICDM PDF | YouTube

How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations

Sérgio Jesus, Catarina Belém, Vladimir Balayan, João Bento, Pedro Saleiro, Pedro Bizarro, João Gama

Published at FAccT 2021 conference

PDF | arXiv | ACM page | YouTube

Railgun: managing large streaming windows under MAD requirements

Ana Sofia Gomes, João Oliveirinha, Pedro Cardoso, Pedro Bizarro

Published at VLDB 2021 conference

Teaching the Machine to Explain Itself using Domain Knowledge

Vladimir Balayan, Pedro Saleiro, Catarina Belém, Ludwig Krippahl, Pedro Bizarro

Published at NeurIPS 2020 - HAMLETS workshop

A Bandit-Based Algorithm for Fairness-Aware Hyperparameter Optimization

André Cruz, Pedro Saleiro, Catarina Belém, Carlos Soares, Pedro Bizarro

PDF | GitHub | arXiv

TEDD: Robust Detection of Unstable Temporal Features

Ricardo Pereira, Bruno Casal Laraña, Nádia Soares, Miguel Araújo

Published at IEEE ICDMW 2020 International Conference on Data Mining Workshops

PDF | bibtex | IEEE

Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcity

Joana Lorenz, Maria Inês Silva, David Aparício, João Tiago Ascensão, Pedro Bizarro

Published at KDD 2020 - Machine Learning in Finance workshop