My work

In this page I summarize some of the main publications, projects and accomplishments from my academic and professional career.

Selected publications

- Unveiling the potential of graph neural networks for robust intrusion detection, ACM Sigmetrics 2022
- IGNNITION: Bridging the gap between graph neural networks and networking systems, IEEE Network 2021
- NetXplain: Real-time explainability of graph neural networks applied to networking, ITU Journal 2021
- The Graph Neural Networking Challange: A Worldwide Competition for Education in AI/ML for Networks, ACM SIGCOMM 2021

Projects

IGNNITION

Resulting from my work in my Bachelor Thesis, my research lab (Barcelona Neural Networking Center) received a European grand to further develop our project, IGNNITION.

This is a framework that provides a code-free interface that permits researchers and practicioners to implement in a matter of hours (instead of days/weeks) potentially very complex Graph Neural Network models. Concretely, complex PyTorch/Tensorflow implementation is substituted by simple natural language descriptiors flexible enough to implement virtually any GNN.

To date, IGNNITION has received over 19k downloads!

Main Accomplishments

- 3rd prize in the Student Research Competition, organized by SIGCOMM '21 (sponsored by Microsoft).
- Awarded as the second-best Bachelor Thesis of my faculty (2020)
- 1st prize in RareHacks for a chatbot that helps patients with pediatric cancer (2019)

About

My name is David Pujol Perich. I am currently a Ph.D student at Hubpba lab from Universitat de Barcelona, where I study the application of efficient Transformer models to video understanding-based tasks. Find my CV here.

I obtained my Bachelors degree in Computer Science at Universitat Polit├Ęcnica de Catalunya (UPC), which I combined with a study exchange at ETHZ, Switzerland. I also obtained my Masters Degree at UPC in Research and Innovation in Informatics with a strong focus on Advanced Computing. I also combined this program with a 1 year exchange at EPFL, Switzerland, where I undertook both courses on Deep Learning and my Master Thesis.

During this time I also combined my studies with professional experience. First of all, I worked as a Machine Learning Research intern at Barcelona Neural Networking Center during almost 2 years. I then worked at LIONS, EPFL as a Machine Learning Research Assistant during 1 year.

All in all, my research interests lay in the field of Deep Learning in general and their application in fields such as Computer Vision or NLP.

I am always open to collaborations and constructive discussions. So do not hesitate to shoot me a mesage!!

Elements

Text

This is bold and this is strong. This is italic and this is emphasized. This is superscript text and this is subscript text. This is underlined and this is code: for (;;) { ... }. Finally, this is a link.


Heading Level 2

Heading Level 3

Heading Level 4

Heading Level 5
Heading Level 6

Blockquote

Fringilla nisl. Donec accumsan interdum nisi, quis tincidunt felis sagittis eget tempus euismod. Vestibulum ante ipsum primis in faucibus vestibulum. Blandit adipiscing eu felis iaculis volutpat ac adipiscing accumsan faucibus. Vestibulum ante ipsum primis in faucibus lorem ipsum dolor sit amet nullam adipiscing eu felis.

Preformatted

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';

Lists

Unordered

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Alternate

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Ordered

  1. Dolor pulvinar etiam.
  2. Etiam vel felis viverra.
  3. Felis enim feugiat.
  4. Dolor pulvinar etiam.
  5. Etiam vel felis lorem.
  6. Felis enim et feugiat.

Icons

Actions

Table

Default

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Alternate

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Buttons

  • Disabled
  • Disabled

Form