1 code implementation • 6 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.
3 code implementations • 8 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.
no code implementations • 11 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.
2 code implementations • 23 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.
no code implementations • 21 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.
1 code implementation • 13 Feb 2020 • Pedro H. C. Avelar, Anderson R. Tavares, Thiago L. T. da Silveira, Cláudio R. Jung, Luís C. Lamb
This paper presents a methodology for image classification using Graph Neural Network (GNN) models.
no code implementations • 26 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.
no code implementations • 19 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.