Search Results for author: An-phi Nguyen

Found 7 papers, 1 papers with code

edGNN: a Simple and Powerful GNN for Directed Labeled Graphs

1 code implementation18 Apr 2019 Guillaume Jaume, An-phi Nguyen, María Rodríguez Martínez, Jean-Philippe Thiran, Maria Gabrani

The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings.

Graph Classification

MonoNet: Towards Interpretable Models by Learning Monotonic Features

no code implementations30 Sep 2019 An-phi Nguyen, María Rodríguez Martínez

Being able to interpret, or explain, the predictions made by a machine learning model is of fundamental importance.

BIG-bench Machine Learning Interpretable Machine Learning

Learning Invariances for Interpretability using Supervised VAE

no code implementations15 Jul 2020 An-phi Nguyen, María Rodríguez Martínez

If we understand a problem, we may introduce inductive biases in our model in the form of invariances.

On quantitative aspects of model interpretability

no code implementations15 Jul 2020 An-phi Nguyen, María Rodríguez Martínez

Despite the growing body of work in interpretable machine learning, it remains unclear how to evaluate different explainability methods without resorting to qualitative assessment and user-studies.

Interpretable Machine Learning

It's FLAN time! Summing feature-wise latent representations for interpretability

no code implementations18 Jun 2021 An-phi Nguyen, Maria Rodriguez Martinez

Interpretability has become a necessary feature for machine learning models deployed in critical scenarios, e. g. legal system, healthcare.

Uncovering Unique Concept Vectors through Latent Space Decomposition

no code implementations13 Jul 2023 Mara Graziani, Laura O' Mahony, An-phi Nguyen, Henning Müller, Vincent Andrearczyk

By decomposing the latent space of a layer in singular vectors and refining them by unsupervised clustering, we uncover concept vectors aligned with directions of high variance that are relevant to the model prediction, and that point to semantically distinct concepts.

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