Search Results for author: Pedro H. C. Avelar

Found 8 papers, 4 papers with code

Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate

1 code implementation6 Sep 2018 Marcelo O. R. Prates, Pedro H. C. Avelar, Luis Lamb

We translate these sentences into English using the Google Translate API, and collect statistics about the frequency of female, male and gender-neutral pronouns in the translated output.

Machine Translation Translation

Learning to Solve NP-Complete Problems - A Graph Neural Network for Decision TSP

3 code implementations8 Sep 2018 Marcelo O. R. Prates, Pedro H. C. Avelar, Henrique Lemos, Luis Lamb, Moshe Vardi

Our model is trained to function as an effective message-passing algorithm in which edges (embedded with their weights) communicate with vertices for a number of iterations after which the model is asked to decide whether a route with cost $<C$ exists.

Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network

no code implementations11 Sep 2018 Pedro H. C. Avelar, Henrique Lemos, Marcelo O. R. Prates, Luis Lamb

We then show that a GNN can be trained to develop a \emph{lingua franca} of vertex embeddings from which all relevant information about any of the trained centrality measures can be decoded.

Relational Reasoning

Typed Graph Networks

2 code implementations23 Jan 2019 Marcelo O. R. Prates, Pedro H. C. Avelar, Henrique Lemos, Marco Gori, Luis Lamb

To illustrate the generality of the original model, we present a Graph Neural Network formalisation, which partitions the vertices of a graph into a number of types.

Discrete and Continuous Deep Residual Learning Over Graphs

no code implementations21 Nov 2019 Pedro H. C. Avelar, Anderson R. Tavares, Marco Gori, Luis C. Lamb

In this paper we propose the use of continuous residual modules for graph kernels in Graph Neural Networks.

Measuring Ethics in AI with AI: A Methodology and Dataset Construction

no code implementations26 Jul 2021 Pedro H. C. Avelar, Rafael B. Audibert, Anderson R. Tavares, Luís C. Lamb

In this paper we propose to use such newfound capabilities of AI technologies to augment our AI measuring capabilities.

Ethics Fairness

Solving the Kidney-Exchange Problem via Graph Neural Networks with No Supervision

no code implementations19 Apr 2023 Pedro Foletto Pimenta, Pedro H. C. Avelar, Luis C. Lamb

The proposed technique consists of two main steps: the first is a Graph Neural Network (GNN) trained without supervision; the second is a deterministic non-learned search heuristic that uses the output of the GNN to find paths and cycles.

Cannot find the paper you are looking for? You can Submit a new open access paper.