GuillaumeSalhaGalvan/GuillaumeSalhaGalvan.github.io
Personal website
Associate Professor in AI
Personal website
Source code from the article "Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction" (Neural Networks, 2022)
Python source code and data from the research article "To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders" by G. Salha-Galvan and J. Xu (WWW 2025)
Paper Lists for Graph Neural Networks
Code for NeurIPS'19 "Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks"
Research team website
Meta-Learning for Few Shot Link Prediction
Geometric Deep Learning Extension Library for PyTorch
Hierarchical Latent Relation Modeling for Collaborative Metric Learning
A simple and elegant jekyll theme for academic personal homepage
This is a TensorFlow implementation of the Adversarially Regularized Graph Autoencoder(ARGA) model as described in our paper: Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., & Zhang, C. (2018). Adversarially Regularized Graph Autoencoder for Graph Embedding, [https://www.ijcai.org/proceedings/2018/0362.pdf].
Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave
A TensorFlow implementation of Baidu's DeepSpeech architecture
Improving Collaborative Metric Learning for Recommendation by a 2-stage negative sampling strategy.
Implementation of Graph Auto-Encoders in TensorFlow
Data Science Summer School tutorial on Bayesian methods
Python code to reproduce the experiments presented in the article Modeling the Music Genre Perception across Language-Bound Cultures, presented at the EMNLP 2020 conference.
Deezer source separation library including pretrained models.
Minimal is a Jekyll theme for GitHub Pages
Repository to reproduce results of "Word2vec applied to Recommendation: Hyperparameters Matter" by H. Caselles-Dupré, F. Lesaint and J. Royo-Letelier. The paper will be published on the 12th ACM Conference on Recommender Systems, Vancouver, Canada, 2nd-7th October 2018
3D force-directed graph component using ThreeJS/WebGL
Software used for generating embeddings from large-scale graph-structured data.
Implementation of Graph Convolutional Networks in TensorFlow
Code for Graphite iterative graph generation
Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville