joaquincabezas

For an original proposal that do logic inference on Hypergraphs I am using NeuraLogic, through a Python frontend (https://github.com/LukasZahradnik/PyNeuraLogic)

I wonder if this is something the author would have enjoyed…

Right now it is working

The GCN implementation is based on the concept of templating (or lifting) which is not exploited in Scallop. In fact, this is the key idea of Neuralogic for joining deep learning and relational-logic representations.

It is explained in the paper "Beyond Graph Neural Networks with Lifted Relational Neural Networks" (https://arxiv.org/abs/2007.06286) and you also have a series of blog posts at https://medium.com/@sir.gustav

I have been a few months into PyNeuraLogic because of its focus on Relational Deep Learning (in particular Lifted Relational Neural Networks). I would say the main selling point is extending GNNs (Graph Neural Networks)

From what I can see on the Scallop website, the focus is on vision and NLP.

So both are similar approaches combining deep learning with symbolic reasoning (and both are based in Datalog) but the problems they are tackling are quite different. Also, both approaches have made it to top conferences like NeurIPS and ICLR, so I guess this field is gaining momentum.

After finishing the game, there is the following message:

> SENT: SEP. 13, 2018 > RCVD: SEP. 13, 2718 > > THANKS FOR PLAYING > > I HAVE PREVIOUSLY BEEN A PROUD SPONSOR OF THE JS13K > COMPETITION SINCE THE VERY FIRST ONE BACK IN 2012. > HOWEVER, THIS YEAR"S COMPETITION WAS MY FIRST ONE > AS A PARTICIPANT AND IT HAS BEEN TREMENDOUS FUN! > > I WANT TO THANK MY DEAR FRIEND ANDREAS LÖSCH OF > NO-FATE.NET FOR COMPOSING SOME AWESOME MUSIC ON > SUCH SHORT NOTICE. > > FURTHER THANKS GO OUT TO THE JS13K STAFF, THE > SONANT-X DEVELOPERS AND ALL OTHER PARTICIPANTS > IN THIS YEAR"S JS13K. SEE YOU NEXT YEAR! > > DOMINIC > END OF TRANSMISSION