Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs


Dec 18, 2021
Shengyu Feng, Subarna Tripathi, Hesham Mostafa, Marcel Nassar, Somdeb Majumdar


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs


Nov 11, 2021
Hesham Mostafa


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Implicit SVD for Graph Representation Learning


Nov 11, 2021
Sami Abu-El-Haija, Hesham Mostafa, Marcel Nassar, Valentino Crespi, Greg Ver Steeg, Aram Galstyan

* Advances in Neural Information Processing Systems (NeurIPS) 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On Local Aggregation in Heterophilic Graphs


Jun 06, 2021
Hesham Mostafa, Marcel Nassar, Somdeb Majumdar


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Attention-based Image Upsampling


Dec 17, 2020
Souvik Kundu, Hesham Mostafa, Sharath Nittur Sridhar, Sairam Sundaresan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Permutohedral-GCN: Graph Convolutional Networks with Global Attention


Mar 02, 2020
Hesham Mostafa, Marcel Nassar


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters


Dec 30, 2019
Hesham Mostafa


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems


Jul 22, 2019
Mark D. McDonnell, Hesham Mostafa, Runchun Wang, Andre van Schaik

* 8 pages, published IEEE conference paper 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization


Mar 19, 2019
Hesham Mostafa, Xin Wang


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>